Add files using upload-large-folder tool
Browse files- .gitattributes +1 -0
- README.md +444 -0
- added_tokens.json +28 -0
- chat_template.jinja +97 -0
- config.json +93 -0
- generation_config.json +14 -0
- merges.txt +0 -0
- model-00001-of-00002.safetensors +3 -0
- model-00002-of-00002.safetensors +3 -0
- model.safetensors.index.json +1162 -0
- quant_log.csv +253 -0
- quantize_config.json +23 -0
- special_tokens_map.json +25 -0
- tokenizer.json +3 -0
- tokenizer_config.json +241 -0
- vocab.json +0 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,444 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model:
|
| 3 |
+
- Qwen/Qwen3-8B
|
| 4 |
+
tags:
|
| 5 |
+
- text-generation-inference
|
| 6 |
+
- transformers
|
| 7 |
+
- qwen3
|
| 8 |
+
- ui-generation
|
| 9 |
+
- tailwind-css
|
| 10 |
+
- html
|
| 11 |
+
- reasoning
|
| 12 |
+
- step-by-step-generation
|
| 13 |
+
- hybrid-thinking
|
| 14 |
+
- tool-calling
|
| 15 |
+
license: apache-2.0
|
| 16 |
+
language:
|
| 17 |
+
- en
|
| 18 |
+
---
|
| 19 |
+
|
| 20 |
+
|
| 21 |
+
|
| 22 |
+
# UIGEN-X-8B Hybrid Reasoning UI Generation Model
|
| 23 |
+
|
| 24 |
+
|
| 25 |
+
|
| 26 |
+
|
| 27 |
+
> Tesslate's hybrid reasoning UI generation model built on Qwen3-8B architecture. Trained to systematically plan, architect, and implement complete user interfaces across modern development stacks.
|
| 28 |
+
|
| 29 |
+
**Live Examples**: [https://uigenoutput.tesslate.com](https://uigenoutput.tesslate.com)
|
| 30 |
+
**Discord Community**: [https://discord.gg/EcCpcTv93U](https://discord.gg/EcCpcTv93U)
|
| 31 |
+
**Website**: [https://tesslate.com](https://tesslate.com)
|
| 32 |
+
|
| 33 |
+
---
|
| 34 |
+
|
| 35 |
+
## Model Architecture
|
| 36 |
+
|
| 37 |
+
UIGEN-X-8B implements **hybrid reasoning** from the Qwen3 family - combining systematic planning with direct implementation. The model follows a structured thinking process:
|
| 38 |
+
|
| 39 |
+
1. **Problem Analysis** — Understanding requirements and constraints
|
| 40 |
+
2. **Architecture Planning** — Component structure and technology decisions
|
| 41 |
+
3. **Design System Definition** — Color schemes, typography, and styling approach
|
| 42 |
+
4. **Implementation Strategy** — Step-by-step code generation with reasoning
|
| 43 |
+
|
| 44 |
+
This hybrid approach enables both thoughtful planning and efficient code generation, making it suitable for complex UI development tasks.
|
| 45 |
+
|
| 46 |
+
---
|
| 47 |
+
|
| 48 |
+
## Complete Technology Coverage
|
| 49 |
+
|
| 50 |
+
UIGEN-X-8B supports **26 major categories** spanning **frameworks and libraries** across **7 platforms**:
|
| 51 |
+
|
| 52 |
+
### Web Frameworks
|
| 53 |
+
- **React**: Next.js, Remix, Gatsby, Create React App, Vite
|
| 54 |
+
- **Vue**: Nuxt.js, Quasar, Gridsome
|
| 55 |
+
- **Angular**: Angular CLI, Ionic Angular
|
| 56 |
+
- **Svelte**: SvelteKit, Astro
|
| 57 |
+
- **Modern**: Solid.js, Qwik, Alpine.js
|
| 58 |
+
- **Static**: Astro, 11ty, Jekyll, Hugo
|
| 59 |
+
|
| 60 |
+
### Styling Systems
|
| 61 |
+
- **Utility-First**: Tailwind CSS, UnoCSS, Windi CSS
|
| 62 |
+
- **CSS-in-JS**: Styled Components, Emotion, Stitches
|
| 63 |
+
- **Component Systems**: Material-UI, Chakra UI, Mantine
|
| 64 |
+
- **Traditional**: Bootstrap, Bulma, Foundation
|
| 65 |
+
- **Design Systems**: Carbon Design, IBM Design Language
|
| 66 |
+
- **Framework-Specific**: Angular Material, Vuetify, Quasar
|
| 67 |
+
|
| 68 |
+
### UI Component Libraries
|
| 69 |
+
- **React**: shadcn/ui, Material-UI, Ant Design, Chakra UI, Mantine, PrimeReact, Headless UI, NextUI, DaisyUI
|
| 70 |
+
- **Vue**: Vuetify, PrimeVue, Quasar, Element Plus, Naive UI
|
| 71 |
+
- **Angular**: Angular Material, PrimeNG, ng-bootstrap, Clarity Design
|
| 72 |
+
- **Svelte**: Svelte Material UI, Carbon Components Svelte
|
| 73 |
+
- **Headless**: Radix UI, Reach UI, Ariakit, React Aria
|
| 74 |
+
|
| 75 |
+
### State Management
|
| 76 |
+
- **React**: Redux Toolkit, Zustand, Jotai, Valtio, Context API
|
| 77 |
+
- **Vue**: Pinia, Vuex, Composables
|
| 78 |
+
- **Angular**: NgRx, Akita, Services
|
| 79 |
+
- **Universal**: MobX, XState, Recoil
|
| 80 |
+
|
| 81 |
+
### Animation Libraries
|
| 82 |
+
- **React**: Framer Motion, React Spring, React Transition Group
|
| 83 |
+
- **Vue**: Vue Transition, Vueuse Motion
|
| 84 |
+
- **Universal**: GSAP, Lottie, CSS Animations, Web Animations API
|
| 85 |
+
- **Mobile**: React Native Reanimated, Expo Animations
|
| 86 |
+
|
| 87 |
+
### Icon Systems
|
| 88 |
+
Lucide, Heroicons, Material Icons, Font Awesome, Ant Design Icons, Bootstrap Icons, Ionicons, Tabler Icons, Feather, Phosphor, React Icons, Vue Icons
|
| 89 |
+
|
| 90 |
+
---
|
| 91 |
+
|
| 92 |
+
## Platform Support
|
| 93 |
+
|
| 94 |
+
### Web Development
|
| 95 |
+
Complete coverage of modern web development from simple HTML/CSS to complex enterprise applications.
|
| 96 |
+
|
| 97 |
+
### Mobile Development
|
| 98 |
+
- **React Native**: Expo, CLI, with navigation and state management
|
| 99 |
+
- **Flutter**: Cross-platform mobile with Material and Cupertino designs
|
| 100 |
+
- **Ionic**: Angular, React, and Vue-based hybrid applications
|
| 101 |
+
|
| 102 |
+
### Desktop Applications
|
| 103 |
+
- **Electron**: Cross-platform desktop apps (Slack, VSCode-style)
|
| 104 |
+
- **Tauri**: Rust-based lightweight desktop applications
|
| 105 |
+
- **Flutter Desktop**: Native desktop performance
|
| 106 |
+
|
| 107 |
+
### Python Applications
|
| 108 |
+
- **Web UI**: Streamlit, Gradio, Flask, FastAPI
|
| 109 |
+
- **Desktop GUI**: Tkinter, PyQt5/6, Kivy, wxPython, Dear PyGui
|
| 110 |
+
|
| 111 |
+
### Development Tools
|
| 112 |
+
Build tools, bundlers, testing frameworks, and development environments.
|
| 113 |
+
|
| 114 |
+
---
|
| 115 |
+
|
| 116 |
+
## Programming Language Support
|
| 117 |
+
|
| 118 |
+
**26 Languages and Approaches**:
|
| 119 |
+
JavaScript, TypeScript, Python, Dart, HTML5, CSS3, SCSS, SASS, Less, PostCSS, CSS Modules, Styled Components, JSX, TSX, Vue SFC, Svelte Components, Angular Templates, Tailwind, PHP
|
| 120 |
+
|
| 121 |
+
---
|
| 122 |
+
|
| 123 |
+
## Visual Style System
|
| 124 |
+
|
| 125 |
+
UIGEN-X-8B includes **21 distinct visual style categories** that can be applied to any framework:
|
| 126 |
+
|
| 127 |
+
### Modern Design Styles
|
| 128 |
+
- **Glassmorphism**: Frosted glass effects with blur and transparency
|
| 129 |
+
- **Neumorphism**: Soft, extruded design elements
|
| 130 |
+
- **Material Design**: Google's design system principles
|
| 131 |
+
- **Fluent Design**: Microsoft's design language
|
| 132 |
+
|
| 133 |
+
### Traditional & Classic
|
| 134 |
+
- **Skeuomorphism**: Real-world object representations
|
| 135 |
+
- **Swiss Design**: Clean typography and grid systems
|
| 136 |
+
- **Bauhaus**: Functional, geometric design principles
|
| 137 |
+
|
| 138 |
+
### Contemporary Trends
|
| 139 |
+
- **Brutalism**: Bold, raw, unconventional layouts
|
| 140 |
+
- **Anti-Design**: Intentionally imperfect, organic aesthetics
|
| 141 |
+
- **Minimalism**: Essential elements only, generous whitespace
|
| 142 |
+
|
| 143 |
+
### Thematic Styles
|
| 144 |
+
- **Cyberpunk**: Neon colors, glitch effects, futuristic elements
|
| 145 |
+
- **Dark Mode**: High contrast, reduced eye strain
|
| 146 |
+
- **Retro-Futurism**: 80s/90s inspired futuristic design
|
| 147 |
+
- **Geocities/90s Web**: Nostalgic early web aesthetics
|
| 148 |
+
|
| 149 |
+
### Experimental
|
| 150 |
+
- **Maximalism**: Rich, layered, abundant visual elements
|
| 151 |
+
- **Madness/Experimental**: Unconventional, boundary-pushing designs
|
| 152 |
+
- **Abstract Shapes**: Geometric, non-representational elements
|
| 153 |
+
|
| 154 |
+
---
|
| 155 |
+
|
| 156 |
+
## Prompt Structure Guide
|
| 157 |
+
|
| 158 |
+
### Basic Structure
|
| 159 |
+
To achieve the best results, use this prompting structure below:
|
| 160 |
+
```
|
| 161 |
+
[Action] + [UI Type] + [Framework Stack] + [Specific Features] + [Optional: Style]
|
| 162 |
+
```
|
| 163 |
+
|
| 164 |
+
### Examples
|
| 165 |
+
|
| 166 |
+
**Simple Component**:
|
| 167 |
+
```
|
| 168 |
+
Create a navigation bar using React + Tailwind CSS with logo, menu items, and mobile hamburger menu
|
| 169 |
+
```
|
| 170 |
+
|
| 171 |
+
**Complex Application**:
|
| 172 |
+
```
|
| 173 |
+
Build a complete e-commerce dashboard using Next.js + TypeScript + Tailwind CSS + shadcn/ui with:
|
| 174 |
+
- Product management (CRUD operations)
|
| 175 |
+
- Order tracking with status updates
|
| 176 |
+
- Customer analytics with charts
|
| 177 |
+
- Responsive design for mobile/desktop
|
| 178 |
+
- Dark mode toggle
|
| 179 |
+
Style: Use a clean, modern glassmorphism aesthetic
|
| 180 |
+
```
|
| 181 |
+
|
| 182 |
+
**Framework-Specific**:
|
| 183 |
+
```
|
| 184 |
+
Design an Angular Material admin panel with:
|
| 185 |
+
- Sidenav with expandable menu items
|
| 186 |
+
- Data tables with sorting and filtering
|
| 187 |
+
- Form validation with reactive forms
|
| 188 |
+
- Charts using ng2-charts
|
| 189 |
+
- SCSS custom theming
|
| 190 |
+
```
|
| 191 |
+
|
| 192 |
+
### Advanced Prompt Techniques
|
| 193 |
+
|
| 194 |
+
**Multi-Page Applications**:
|
| 195 |
+
```
|
| 196 |
+
Create a complete SaaS application using Vue 3 + Nuxt 3 + Tailwind CSS + Pinia:
|
| 197 |
+
|
| 198 |
+
Pages needed:
|
| 199 |
+
1. Landing page with hero, features, pricing
|
| 200 |
+
2. Dashboard with metrics and quick actions
|
| 201 |
+
3. Settings page with user preferences
|
| 202 |
+
4. Billing page with subscription management
|
| 203 |
+
|
| 204 |
+
Include: Navigation between pages, state management, responsive design
|
| 205 |
+
Style: Professional, modern with subtle animations
|
| 206 |
+
```
|
| 207 |
+
|
| 208 |
+
**Style Mixing**:
|
| 209 |
+
```
|
| 210 |
+
Build a portfolio website using Svelte + SvelteKit + Tailwind CSS combining:
|
| 211 |
+
- Minimalist layout principles
|
| 212 |
+
- Cyberpunk color scheme (neon accents)
|
| 213 |
+
- Smooth animations for page transitions
|
| 214 |
+
- Typography-driven content sections
|
| 215 |
+
```
|
| 216 |
+
|
| 217 |
+
---
|
| 218 |
+
|
| 219 |
+
## Tool Calling & Agentic Usage
|
| 220 |
+
|
| 221 |
+
UIGEN-X-8B supports **function calling** for dynamic asset integration and enhanced development workflows.
|
| 222 |
+
|
| 223 |
+
### Image Integration with Unsplash
|
| 224 |
+
|
| 225 |
+
Register tools for dynamic image fetching:
|
| 226 |
+
|
| 227 |
+
```json
|
| 228 |
+
{
|
| 229 |
+
"type": "function",
|
| 230 |
+
"function": {
|
| 231 |
+
"name": "fetch_unsplash_image",
|
| 232 |
+
"description": "Fetch high-quality images from Unsplash for UI mockups",
|
| 233 |
+
"parameters": {
|
| 234 |
+
"type": "object",
|
| 235 |
+
"properties": {
|
| 236 |
+
"query": {
|
| 237 |
+
"type": "string",
|
| 238 |
+
"description": "Search term for image (e.g., 'modern office', 'technology', 'nature')"
|
| 239 |
+
},
|
| 240 |
+
"orientation": {
|
| 241 |
+
"type": "string",
|
| 242 |
+
"enum": ["landscape", "portrait", "squarish"],
|
| 243 |
+
"description": "Image orientation"
|
| 244 |
+
},
|
| 245 |
+
"size": {
|
| 246 |
+
"type": "string",
|
| 247 |
+
"enum": ["small", "regular", "full"],
|
| 248 |
+
"description": "Image size"
|
| 249 |
+
}
|
| 250 |
+
},
|
| 251 |
+
"required": ["query"]
|
| 252 |
+
}
|
| 253 |
+
}
|
| 254 |
+
}
|
| 255 |
+
```
|
| 256 |
+
|
| 257 |
+
### Content Generation Tools
|
| 258 |
+
|
| 259 |
+
```json
|
| 260 |
+
{
|
| 261 |
+
"type": "function",
|
| 262 |
+
"function": {
|
| 263 |
+
"name": "generate_content",
|
| 264 |
+
"description": "Generate realistic content for UI components",
|
| 265 |
+
"parameters": {
|
| 266 |
+
"type": "object",
|
| 267 |
+
"properties": {
|
| 268 |
+
"type": {
|
| 269 |
+
"type": "string",
|
| 270 |
+
"enum": ["user_profiles", "product_data", "blog_posts", "testimonials"],
|
| 271 |
+
"description": "Type of content to generate"
|
| 272 |
+
},
|
| 273 |
+
"count": {
|
| 274 |
+
"type": "integer",
|
| 275 |
+
"description": "Number of items to generate"
|
| 276 |
+
},
|
| 277 |
+
"theme": {
|
| 278 |
+
"type": "string",
|
| 279 |
+
"description": "Content theme or industry"
|
| 280 |
+
}
|
| 281 |
+
},
|
| 282 |
+
"required": ["type", "count"]
|
| 283 |
+
}
|
| 284 |
+
}
|
| 285 |
+
}
|
| 286 |
+
```
|
| 287 |
+
|
| 288 |
+
### Complete Agentic Workflow Example
|
| 289 |
+
|
| 290 |
+
```python
|
| 291 |
+
# 1. Plan the application
|
| 292 |
+
response = model.chat([
|
| 293 |
+
{"role": "user", "content": "Plan a complete travel booking website using React + Next.js + Tailwind CSS + shadcn/ui"}
|
| 294 |
+
], tools=[fetch_unsplash_image, generate_content])
|
| 295 |
+
|
| 296 |
+
# 2. The model will reason through the requirements and call tools:
|
| 297 |
+
# - fetch_unsplash_image(query="travel destinations", orientation="landscape")
|
| 298 |
+
# - generate_content(type="destinations", count=10, theme="popular travel")
|
| 299 |
+
# - fetch_unsplash_image(query="hotel rooms", orientation="landscape")
|
| 300 |
+
|
| 301 |
+
# 3. Generate complete implementation with real assets
|
| 302 |
+
final_response = model.chat([
|
| 303 |
+
{"role": "user", "content": "Now implement the complete website with the fetched images and content"}
|
| 304 |
+
])
|
| 305 |
+
```
|
| 306 |
+
|
| 307 |
+
### Tool Integration Patterns
|
| 308 |
+
|
| 309 |
+
**Dynamic Asset Loading**:
|
| 310 |
+
- Fetch relevant images during UI generation
|
| 311 |
+
- Generate realistic content for components
|
| 312 |
+
- Create cohesive color palettes from images
|
| 313 |
+
- Optimize assets for web performance
|
| 314 |
+
|
| 315 |
+
**Multi-Step Development**:
|
| 316 |
+
- Plan application architecture
|
| 317 |
+
- Generate individual components
|
| 318 |
+
- Integrate components into pages
|
| 319 |
+
- Apply consistent styling and theming
|
| 320 |
+
- Test responsive behavior
|
| 321 |
+
|
| 322 |
+
**Content-Aware Design**:
|
| 323 |
+
- Adapt layouts based on content types
|
| 324 |
+
- Optimize typography for readability
|
| 325 |
+
- Create responsive image galleries
|
| 326 |
+
- Generate accessible alt text
|
| 327 |
+
|
| 328 |
+
---
|
| 329 |
+
|
| 330 |
+
## Inference Configuration
|
| 331 |
+
|
| 332 |
+
### Optimal Parameters
|
| 333 |
+
```python
|
| 334 |
+
{
|
| 335 |
+
"temperature": 0.6, # Balanced creativity and consistency (make it lower if quantized!!!!)
|
| 336 |
+
"top_p": 0.9, # Nucleus sampling for quality
|
| 337 |
+
"top_k": 40, # Vocabulary restriction
|
| 338 |
+
"max_tokens": 25000, # Full component generation
|
| 339 |
+
"repetition_penalty": 1.1, # Avoid repetitive patterns
|
| 340 |
+
}
|
| 341 |
+
```
|
| 342 |
+
|
| 343 |
+
---
|
| 344 |
+
|
| 345 |
+
## Use Cases & Applications
|
| 346 |
+
|
| 347 |
+
### Rapid Prototyping
|
| 348 |
+
- Quick mockups for client presentations
|
| 349 |
+
- A/B testing different design approaches
|
| 350 |
+
- Concept validation with interactive prototypes
|
| 351 |
+
|
| 352 |
+
### Production Development
|
| 353 |
+
- Component library creation
|
| 354 |
+
- Design system implementation
|
| 355 |
+
- Template and boilerplate generation
|
| 356 |
+
|
| 357 |
+
### Educational & Learning
|
| 358 |
+
- Teaching modern web development
|
| 359 |
+
- Framework comparison and evaluation
|
| 360 |
+
- Best practices demonstration
|
| 361 |
+
|
| 362 |
+
### Enterprise Solutions
|
| 363 |
+
- Dashboard and admin panel generation
|
| 364 |
+
- Internal tool development
|
| 365 |
+
- Legacy system modernization
|
| 366 |
+
|
| 367 |
+
---
|
| 368 |
+
|
| 369 |
+
## Technical Requirements
|
| 370 |
+
|
| 371 |
+
### Hardware
|
| 372 |
+
- **GPU**: 8GB+ VRAM recommended (RTX 3080/4070 or equivalent)
|
| 373 |
+
- **RAM**: 16GB system memory minimum
|
| 374 |
+
- **Storage**: 20GB for model weights and cache
|
| 375 |
+
|
| 376 |
+
### Software
|
| 377 |
+
- **Python**: 3.8+ with transformers, torch, unsloth
|
| 378 |
+
- **Node.js**: For running generated JavaScript/TypeScript code
|
| 379 |
+
- **Browser**: Modern browser for testing generated UIs
|
| 380 |
+
|
| 381 |
+
### Integration
|
| 382 |
+
- Compatible with HuggingFace transformers
|
| 383 |
+
- Supports GGML/GGUF quantization
|
| 384 |
+
- Works with text-generation-webui
|
| 385 |
+
- API-ready for production deployment
|
| 386 |
+
|
| 387 |
+
---
|
| 388 |
+
|
| 389 |
+
## Limitations & Considerations
|
| 390 |
+
|
| 391 |
+
- **Token Usage**: Reasoning process increases token consumption
|
| 392 |
+
- **Complex Logic**: Focuses on UI structure rather than business logic
|
| 393 |
+
- **Real-time Features**: Generated code requires backend integration
|
| 394 |
+
- **Testing**: Output may need manual testing and refinement
|
| 395 |
+
- **Accessibility**: While ARIA-aware, manual a11y testing recommended
|
| 396 |
+
|
| 397 |
+
---
|
| 398 |
+
|
| 399 |
+
## Community & Support
|
| 400 |
+
|
| 401 |
+
**Discord**: [https://discord.gg/EcCpcTv93U](https://discord.gg/EcCpcTv93U)
|
| 402 |
+
**Website**: [https://tesslate.com](https://tesslate.com)
|
| 403 |
+
**Examples**: [https://uigenoutput.tesslate.com](https://uigenoutput.tesslate.com)
|
| 404 |
+
|
| 405 |
+
Join our community to share creations, get help, and contribute to the ecosystem.
|
| 406 |
+
|
| 407 |
+
---
|
| 408 |
+
|
| 409 |
+
## Citation
|
| 410 |
+
|
| 411 |
+
```bibtex
|
| 412 |
+
@misc{tesslate_uigen_x_2025,
|
| 413 |
+
title={UIGEN-X-8B: Hybrid Reasoning UI Generation with Qwen3},
|
| 414 |
+
author={Tesslate Team},
|
| 415 |
+
year={2025},
|
| 416 |
+
publisher={Tesslate},
|
| 417 |
+
url={https://huggingface.co/tesslate/UIGEN-X-8B}
|
| 418 |
+
}
|
| 419 |
+
```
|
| 420 |
+
|
| 421 |
+
---
|
| 422 |
+
|
| 423 |
+
|
| 424 |
+
<img src="https://cdn-uploads.huggingface.co/production/uploads/64d1129297ca59bcf7458d07/ZhW150gEhg0lkXoSjkiiU.png" alt="UI Screenshot 1" width="400">
|
| 425 |
+
<img src="https://cdn-uploads.huggingface.co/production/uploads/64d1129297ca59bcf7458d07/NdxVu6Zv6beigOYjbKCl1.png" alt="UI Screenshot 2" width="400">
|
| 426 |
+
<img src="https://cdn-uploads.huggingface.co/production/uploads/64d1129297ca59bcf7458d07/RX8po_paCIxrrcTvZ3xfA.png" alt="UI Screenshot 3" width="400">
|
| 427 |
+
<img src="https://cdn-uploads.huggingface.co/production/uploads/64d1129297ca59bcf7458d07/DBssA7zan39uxy9HQOo5N.png" alt="UI Screenshot 4" width="400">
|
| 428 |
+
<img src="https://cdn-uploads.huggingface.co/production/uploads/64d1129297ca59bcf7458d07/ttljEdBcYh1tkmyrCUQku.png" alt="UI Screenshot 5" width="400">
|
| 429 |
+
<img src="https://cdn-uploads.huggingface.co/production/uploads/64d1129297ca59bcf7458d07/duLxNQAuqv1FPVlsmQsWr.png" alt="UI Screenshot 6" width="400">
|
| 430 |
+
<img src="https://cdn-uploads.huggingface.co/production/uploads/64d1129297ca59bcf7458d07/ja2nhpNrvucf_zwCARXxa.png" alt="UI Screenshot 7" width="400">
|
| 431 |
+
<img src="https://cdn-uploads.huggingface.co/production/uploads/64d1129297ca59bcf7458d07/ca0f_8U9HQdaSVAejpzPn.png" alt="UI Screenshot 8" width="400">
|
| 432 |
+
<img src="https://cdn-uploads.huggingface.co/production/uploads/64d1129297ca59bcf7458d07/gzZF2CiOjyEbPAPRYSV-N.png" alt="UI Screenshot 9" width="400">
|
| 433 |
+
<img src="https://cdn-uploads.huggingface.co/production/uploads/64d1129297ca59bcf7458d07/y8wB78PffUUoVLzw3al2R.png" alt="UI Screenshot 10" width="400">
|
| 434 |
+
<img src="https://cdn-uploads.huggingface.co/production/uploads/64d1129297ca59bcf7458d07/M12dGr0xArAIF7gANSC5T.png" alt="UI Screenshot 11" width="400">
|
| 435 |
+
<img src="https://cdn-uploads.huggingface.co/production/uploads/64d1129297ca59bcf7458d07/t7r7cYlUwmI1QQf3fxO7o.png" alt="UI Screenshot 12" width="400">
|
| 436 |
+
<img src="https://cdn-uploads.huggingface.co/production/uploads/64d1129297ca59bcf7458d07/-uCIIJqTrrY9xkJHKCEqC.png" alt="UI Screenshot 13" width="400">
|
| 437 |
+
<img src="https://cdn-uploads.huggingface.co/production/uploads/64d1129297ca59bcf7458d07/eqT3IUWaPtoNQb-IWQNuy.png" alt="UI Screenshot 14" width="400">
|
| 438 |
+
<img src="https://cdn-uploads.huggingface.co/production/uploads/64d1129297ca59bcf7458d07/RhbGMcxCNlMIXRLEacUGi.png" alt="UI Screenshot 15" width="400">
|
| 439 |
+
<img src="https://cdn-uploads.huggingface.co/production/uploads/64d1129297ca59bcf7458d07/FWhs43BKkXku12MwiW0v9.png" alt="UI Screenshot 16" width="400">
|
| 440 |
+
<img src="https://cdn-uploads.huggingface.co/production/uploads/67db34a5e7f1d129b294e2af/ILHx-xcn18cyDLX5a63xV.png" alt="UIGEN-X UI Screenshot 1" width="400">
|
| 441 |
+
<img src="https://cdn-uploads.huggingface.co/production/uploads/67db34a5e7f1d129b294e2af/A-zKo1J4HYftjiOjq_GB4.png" alt="UIGEN-X UI Screenshot 2" width="400">
|
| 442 |
+
|
| 443 |
+
|
| 444 |
+
*Built with hybrid reasoning capabilities from Qwen3, UIGEN-X-8B represents a comprehensive approach to AI-driven UI development across the entire modern web development ecosystem.*
|
added_tokens.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</think>": 151668,
|
| 3 |
+
"</tool_call>": 151658,
|
| 4 |
+
"</tool_response>": 151666,
|
| 5 |
+
"<think>": 151667,
|
| 6 |
+
"<tool_call>": 151657,
|
| 7 |
+
"<tool_response>": 151665,
|
| 8 |
+
"<|box_end|>": 151649,
|
| 9 |
+
"<|box_start|>": 151648,
|
| 10 |
+
"<|endoftext|>": 151643,
|
| 11 |
+
"<|file_sep|>": 151664,
|
| 12 |
+
"<|fim_middle|>": 151660,
|
| 13 |
+
"<|fim_pad|>": 151662,
|
| 14 |
+
"<|fim_prefix|>": 151659,
|
| 15 |
+
"<|fim_suffix|>": 151661,
|
| 16 |
+
"<|im_end|>": 151645,
|
| 17 |
+
"<|im_start|>": 151644,
|
| 18 |
+
"<|image_pad|>": 151655,
|
| 19 |
+
"<|object_ref_end|>": 151647,
|
| 20 |
+
"<|object_ref_start|>": 151646,
|
| 21 |
+
"<|quad_end|>": 151651,
|
| 22 |
+
"<|quad_start|>": 151650,
|
| 23 |
+
"<|repo_name|>": 151663,
|
| 24 |
+
"<|video_pad|>": 151656,
|
| 25 |
+
"<|vision_end|>": 151653,
|
| 26 |
+
"<|vision_pad|>": 151654,
|
| 27 |
+
"<|vision_start|>": 151652
|
| 28 |
+
}
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,97 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- if tools %}
|
| 2 |
+
{{- '<|im_start|>system\n' }}
|
| 3 |
+
{%- if messages[0].role == 'system' %}
|
| 4 |
+
{{- messages[0].content + '\n\n' }}
|
| 5 |
+
{%- endif %}
|
| 6 |
+
{{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
| 7 |
+
{%- for tool in tools %}
|
| 8 |
+
{{- "\n" }}
|
| 9 |
+
{{- tool | tojson }}
|
| 10 |
+
{%- endfor %}
|
| 11 |
+
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
| 12 |
+
{%- else %}
|
| 13 |
+
{%- if messages[0].role == 'system' %}
|
| 14 |
+
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
|
| 15 |
+
{%- endif %}
|
| 16 |
+
{%- endif %}
|
| 17 |
+
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
| 18 |
+
{%- for forward_message in messages %}
|
| 19 |
+
{%- set index = (messages|length - 1) - loop.index0 %}
|
| 20 |
+
{%- set message = messages[index] %}
|
| 21 |
+
{%- set tool_start = '<tool_response>' %}
|
| 22 |
+
{%- set tool_start_length = tool_start|length %}
|
| 23 |
+
{%- set start_of_message = message.content[:tool_start_length] %}
|
| 24 |
+
{%- set tool_end = '</tool_response>' %}
|
| 25 |
+
{%- set tool_end_length = tool_end|length %}
|
| 26 |
+
{%- set start_pos = (message.content|length) - tool_end_length %}
|
| 27 |
+
{%- if start_pos < 0 %}
|
| 28 |
+
{%- set start_pos = 0 %}
|
| 29 |
+
{%- endif %}
|
| 30 |
+
{%- set end_of_message = message.content[start_pos:] %}
|
| 31 |
+
{%- if ns.multi_step_tool and message.role == "user" and not(start_of_message == tool_start and end_of_message == tool_end) %}
|
| 32 |
+
{%- set ns.multi_step_tool = false %}
|
| 33 |
+
{%- set ns.last_query_index = index %}
|
| 34 |
+
{%- endif %}
|
| 35 |
+
{%- endfor %}
|
| 36 |
+
{%- for message in messages %}
|
| 37 |
+
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
| 38 |
+
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
| 39 |
+
{%- elif message.role == "assistant" %}
|
| 40 |
+
{%- set content = message.content %}
|
| 41 |
+
{%- set reasoning_content = '' %}
|
| 42 |
+
{%- if message.reasoning_content is defined and message.reasoning_content is not none %}
|
| 43 |
+
{%- set reasoning_content = message.reasoning_content %}
|
| 44 |
+
{%- else %}
|
| 45 |
+
{%- if '</think>' in message.content %}
|
| 46 |
+
{%- set content = (message.content.split('</think>')|last).lstrip('\n') %}
|
| 47 |
+
{%- set reasoning_content = (message.content.split('</think>')|first).rstrip('\n') %}
|
| 48 |
+
{%- set reasoning_content = (reasoning_content.split('<think>')|last).lstrip('\n') %}
|
| 49 |
+
{%- endif %}
|
| 50 |
+
{%- endif %}
|
| 51 |
+
{%- if loop.index0 > ns.last_query_index %}
|
| 52 |
+
{%- if loop.last or (not loop.last and reasoning_content) %}
|
| 53 |
+
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
|
| 54 |
+
{%- else %}
|
| 55 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 56 |
+
{%- endif %}
|
| 57 |
+
{%- else %}
|
| 58 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 59 |
+
{%- endif %}
|
| 60 |
+
{%- if message.tool_calls %}
|
| 61 |
+
{%- for tool_call in message.tool_calls %}
|
| 62 |
+
{%- if (loop.first and content) or (not loop.first) %}
|
| 63 |
+
{{- '\n' }}
|
| 64 |
+
{%- endif %}
|
| 65 |
+
{%- if tool_call.function %}
|
| 66 |
+
{%- set tool_call = tool_call.function %}
|
| 67 |
+
{%- endif %}
|
| 68 |
+
{{- '<tool_call>\n{"name": "' }}
|
| 69 |
+
{{- tool_call.name }}
|
| 70 |
+
{{- '", "arguments": ' }}
|
| 71 |
+
{%- if tool_call.arguments is string %}
|
| 72 |
+
{{- tool_call.arguments }}
|
| 73 |
+
{%- else %}
|
| 74 |
+
{{- tool_call.arguments | tojson }}
|
| 75 |
+
{%- endif %}
|
| 76 |
+
{{- '}\n</tool_call>' }}
|
| 77 |
+
{%- endfor %}
|
| 78 |
+
{%- endif %}
|
| 79 |
+
{{- '<|im_end|>\n' }}
|
| 80 |
+
{%- elif message.role == "tool" %}
|
| 81 |
+
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
| 82 |
+
{{- '<|im_start|>user' }}
|
| 83 |
+
{%- endif %}
|
| 84 |
+
{{- '\n<tool_response>\n' }}
|
| 85 |
+
{{- message.content }}
|
| 86 |
+
{{- '\n</tool_response>' }}
|
| 87 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 88 |
+
{{- '<|im_end|>\n' }}
|
| 89 |
+
{%- endif %}
|
| 90 |
+
{%- endif %}
|
| 91 |
+
{%- endfor %}
|
| 92 |
+
{%- if add_generation_prompt %}
|
| 93 |
+
{{- '<|im_start|>assistant\n' }}
|
| 94 |
+
{%- if enable_thinking is defined and enable_thinking is false %}
|
| 95 |
+
{{- '<think>\n\n</think>\n\n' }}
|
| 96 |
+
{%- endif %}
|
| 97 |
+
{%- endif %}
|
config.json
ADDED
|
@@ -0,0 +1,93 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"eos_token_id": 151645,
|
| 8 |
+
"head_dim": 128,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 4096,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 12288,
|
| 13 |
+
"layer_types": [
|
| 14 |
+
"full_attention",
|
| 15 |
+
"full_attention",
|
| 16 |
+
"full_attention",
|
| 17 |
+
"full_attention",
|
| 18 |
+
"full_attention",
|
| 19 |
+
"full_attention",
|
| 20 |
+
"full_attention",
|
| 21 |
+
"full_attention",
|
| 22 |
+
"full_attention",
|
| 23 |
+
"full_attention",
|
| 24 |
+
"full_attention",
|
| 25 |
+
"full_attention",
|
| 26 |
+
"full_attention",
|
| 27 |
+
"full_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"full_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"full_attention",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"full_attention",
|
| 35 |
+
"full_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"full_attention",
|
| 38 |
+
"full_attention",
|
| 39 |
+
"full_attention",
|
| 40 |
+
"full_attention",
|
| 41 |
+
"full_attention",
|
| 42 |
+
"full_attention",
|
| 43 |
+
"full_attention",
|
| 44 |
+
"full_attention",
|
| 45 |
+
"full_attention",
|
| 46 |
+
"full_attention",
|
| 47 |
+
"full_attention",
|
| 48 |
+
"full_attention",
|
| 49 |
+
"full_attention"
|
| 50 |
+
],
|
| 51 |
+
"max_position_embeddings": 40960,
|
| 52 |
+
"max_window_layers": 36,
|
| 53 |
+
"model_type": "qwen3",
|
| 54 |
+
"num_attention_heads": 32,
|
| 55 |
+
"num_hidden_layers": 36,
|
| 56 |
+
"num_key_value_heads": 8,
|
| 57 |
+
"pad_token_id": 151654,
|
| 58 |
+
"quantization_config": {
|
| 59 |
+
"bits": 4,
|
| 60 |
+
"checkpoint_format": "gptq",
|
| 61 |
+
"desc_act": true,
|
| 62 |
+
"group_size": 128,
|
| 63 |
+
"lm_head": false,
|
| 64 |
+
"meta": {
|
| 65 |
+
"damp_auto_increment": 0.0025,
|
| 66 |
+
"damp_percent": 0.01,
|
| 67 |
+
"mse": 0.0,
|
| 68 |
+
"quantizer": [
|
| 69 |
+
"gptqmodel:3.0.0-dev"
|
| 70 |
+
],
|
| 71 |
+
"static_groups": false,
|
| 72 |
+
"true_sequential": true,
|
| 73 |
+
"uri": "https://github.com/modelcloud/gptqmodel",
|
| 74 |
+
"v2": false,
|
| 75 |
+
"v2_alpha": 0.25
|
| 76 |
+
},
|
| 77 |
+
"pack_dtype": "int32",
|
| 78 |
+
"quant_method": "gptq",
|
| 79 |
+
"sym": true
|
| 80 |
+
},
|
| 81 |
+
"rms_norm_eps": 1e-06,
|
| 82 |
+
"rope_scaling": null,
|
| 83 |
+
"rope_theta": 1000000,
|
| 84 |
+
"sliding_window": null,
|
| 85 |
+
"tie_word_embeddings": false,
|
| 86 |
+
"torch_dtype": "bfloat16",
|
| 87 |
+
"transformers_version": "4.52.3",
|
| 88 |
+
"unsloth_fixed": true,
|
| 89 |
+
"unsloth_version": "2025.7.4",
|
| 90 |
+
"use_cache": true,
|
| 91 |
+
"use_sliding_window": false,
|
| 92 |
+
"vocab_size": 151936
|
| 93 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
151645,
|
| 6 |
+
151643
|
| 7 |
+
],
|
| 8 |
+
"max_length": 40960,
|
| 9 |
+
"pad_token_id": 151654,
|
| 10 |
+
"temperature": 0.6,
|
| 11 |
+
"top_k": 20,
|
| 12 |
+
"top_p": 0.95,
|
| 13 |
+
"transformers_version": "4.52.3"
|
| 14 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7dde40d26f06496da4b75ff20ab40dad0daa9d5342dd2c26f9915bcc5bfcb1fb
|
| 3 |
+
size 3977460544
|
model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a5276f9d676038e012b3bc7f80c14c3480211e9e51b3a199b769e673a99106e7
|
| 3 |
+
size 2126456480
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,1162 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 6103787520
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"lm_head.weight": "model-00002-of-00002.safetensors",
|
| 7 |
+
"model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
| 8 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 9 |
+
"model.layers.0.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 10 |
+
"model.layers.0.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
| 11 |
+
"model.layers.0.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 12 |
+
"model.layers.0.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
| 13 |
+
"model.layers.0.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 14 |
+
"model.layers.0.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
| 15 |
+
"model.layers.0.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 16 |
+
"model.layers.0.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
| 17 |
+
"model.layers.0.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 18 |
+
"model.layers.0.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
| 19 |
+
"model.layers.0.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 20 |
+
"model.layers.0.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 21 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 22 |
+
"model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 23 |
+
"model.layers.0.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 24 |
+
"model.layers.0.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 25 |
+
"model.layers.0.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 26 |
+
"model.layers.0.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 27 |
+
"model.layers.0.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 28 |
+
"model.layers.0.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
| 29 |
+
"model.layers.0.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 30 |
+
"model.layers.0.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 31 |
+
"model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 32 |
+
"model.layers.0.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 33 |
+
"model.layers.0.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 34 |
+
"model.layers.0.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 35 |
+
"model.layers.0.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 36 |
+
"model.layers.0.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 37 |
+
"model.layers.0.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 38 |
+
"model.layers.0.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 39 |
+
"model.layers.0.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 40 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 41 |
+
"model.layers.1.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 42 |
+
"model.layers.1.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
| 43 |
+
"model.layers.1.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 44 |
+
"model.layers.1.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
| 45 |
+
"model.layers.1.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 46 |
+
"model.layers.1.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
| 47 |
+
"model.layers.1.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 48 |
+
"model.layers.1.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
| 49 |
+
"model.layers.1.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 50 |
+
"model.layers.1.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
| 51 |
+
"model.layers.1.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 52 |
+
"model.layers.1.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 53 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 54 |
+
"model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 55 |
+
"model.layers.1.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 56 |
+
"model.layers.1.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 57 |
+
"model.layers.1.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 58 |
+
"model.layers.1.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 59 |
+
"model.layers.1.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 60 |
+
"model.layers.1.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
| 61 |
+
"model.layers.1.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 62 |
+
"model.layers.1.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 63 |
+
"model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 64 |
+
"model.layers.1.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 65 |
+
"model.layers.1.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 66 |
+
"model.layers.1.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 67 |
+
"model.layers.1.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 68 |
+
"model.layers.1.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 69 |
+
"model.layers.1.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 70 |
+
"model.layers.1.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 71 |
+
"model.layers.1.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 72 |
+
"model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 73 |
+
"model.layers.10.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 74 |
+
"model.layers.10.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
| 75 |
+
"model.layers.10.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 76 |
+
"model.layers.10.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
| 77 |
+
"model.layers.10.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 78 |
+
"model.layers.10.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
| 79 |
+
"model.layers.10.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 80 |
+
"model.layers.10.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
| 81 |
+
"model.layers.10.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 82 |
+
"model.layers.10.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
| 83 |
+
"model.layers.10.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 84 |
+
"model.layers.10.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 85 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 86 |
+
"model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 87 |
+
"model.layers.10.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 88 |
+
"model.layers.10.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 89 |
+
"model.layers.10.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 90 |
+
"model.layers.10.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 91 |
+
"model.layers.10.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 92 |
+
"model.layers.10.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
| 93 |
+
"model.layers.10.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 94 |
+
"model.layers.10.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 95 |
+
"model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 96 |
+
"model.layers.10.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 97 |
+
"model.layers.10.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 98 |
+
"model.layers.10.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 99 |
+
"model.layers.10.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 100 |
+
"model.layers.10.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 101 |
+
"model.layers.10.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 102 |
+
"model.layers.10.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 103 |
+
"model.layers.10.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 104 |
+
"model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 105 |
+
"model.layers.11.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 106 |
+
"model.layers.11.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
| 107 |
+
"model.layers.11.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 108 |
+
"model.layers.11.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
| 109 |
+
"model.layers.11.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 110 |
+
"model.layers.11.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
| 111 |
+
"model.layers.11.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 112 |
+
"model.layers.11.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
| 113 |
+
"model.layers.11.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 114 |
+
"model.layers.11.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
| 115 |
+
"model.layers.11.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 116 |
+
"model.layers.11.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 117 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 118 |
+
"model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 119 |
+
"model.layers.11.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 120 |
+
"model.layers.11.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 121 |
+
"model.layers.11.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 122 |
+
"model.layers.11.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 123 |
+
"model.layers.11.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 124 |
+
"model.layers.11.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
| 125 |
+
"model.layers.11.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 126 |
+
"model.layers.11.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 127 |
+
"model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 128 |
+
"model.layers.11.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 129 |
+
"model.layers.11.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 130 |
+
"model.layers.11.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 131 |
+
"model.layers.11.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 132 |
+
"model.layers.11.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 133 |
+
"model.layers.11.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 134 |
+
"model.layers.11.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 135 |
+
"model.layers.11.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 136 |
+
"model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 137 |
+
"model.layers.12.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 138 |
+
"model.layers.12.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
| 139 |
+
"model.layers.12.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 140 |
+
"model.layers.12.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
| 141 |
+
"model.layers.12.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 142 |
+
"model.layers.12.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
| 143 |
+
"model.layers.12.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 144 |
+
"model.layers.12.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
| 145 |
+
"model.layers.12.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 146 |
+
"model.layers.12.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
| 147 |
+
"model.layers.12.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 148 |
+
"model.layers.12.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 149 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 150 |
+
"model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 151 |
+
"model.layers.12.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 152 |
+
"model.layers.12.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 153 |
+
"model.layers.12.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 154 |
+
"model.layers.12.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 155 |
+
"model.layers.12.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 156 |
+
"model.layers.12.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
| 157 |
+
"model.layers.12.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 158 |
+
"model.layers.12.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 159 |
+
"model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 160 |
+
"model.layers.12.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 161 |
+
"model.layers.12.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 162 |
+
"model.layers.12.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 163 |
+
"model.layers.12.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 164 |
+
"model.layers.12.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 165 |
+
"model.layers.12.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 166 |
+
"model.layers.12.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 167 |
+
"model.layers.12.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 168 |
+
"model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 169 |
+
"model.layers.13.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 170 |
+
"model.layers.13.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
| 171 |
+
"model.layers.13.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 172 |
+
"model.layers.13.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
| 173 |
+
"model.layers.13.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 174 |
+
"model.layers.13.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
| 175 |
+
"model.layers.13.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 176 |
+
"model.layers.13.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
| 177 |
+
"model.layers.13.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 178 |
+
"model.layers.13.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
| 179 |
+
"model.layers.13.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 180 |
+
"model.layers.13.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 181 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 182 |
+
"model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 183 |
+
"model.layers.13.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 184 |
+
"model.layers.13.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 185 |
+
"model.layers.13.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 186 |
+
"model.layers.13.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 187 |
+
"model.layers.13.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 188 |
+
"model.layers.13.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
| 189 |
+
"model.layers.13.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 190 |
+
"model.layers.13.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 191 |
+
"model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 192 |
+
"model.layers.13.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 193 |
+
"model.layers.13.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 194 |
+
"model.layers.13.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 195 |
+
"model.layers.13.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 196 |
+
"model.layers.13.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 197 |
+
"model.layers.13.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 198 |
+
"model.layers.13.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 199 |
+
"model.layers.13.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 200 |
+
"model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 201 |
+
"model.layers.14.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 202 |
+
"model.layers.14.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
| 203 |
+
"model.layers.14.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 204 |
+
"model.layers.14.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
| 205 |
+
"model.layers.14.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 206 |
+
"model.layers.14.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
| 207 |
+
"model.layers.14.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 208 |
+
"model.layers.14.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
| 209 |
+
"model.layers.14.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 210 |
+
"model.layers.14.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
| 211 |
+
"model.layers.14.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 212 |
+
"model.layers.14.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 213 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 214 |
+
"model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 215 |
+
"model.layers.14.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 216 |
+
"model.layers.14.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 217 |
+
"model.layers.14.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 218 |
+
"model.layers.14.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 219 |
+
"model.layers.14.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 220 |
+
"model.layers.14.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
| 221 |
+
"model.layers.14.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 222 |
+
"model.layers.14.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 223 |
+
"model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 224 |
+
"model.layers.14.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 225 |
+
"model.layers.14.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 226 |
+
"model.layers.14.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 227 |
+
"model.layers.14.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 228 |
+
"model.layers.14.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 229 |
+
"model.layers.14.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 230 |
+
"model.layers.14.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 231 |
+
"model.layers.14.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 232 |
+
"model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 233 |
+
"model.layers.15.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 234 |
+
"model.layers.15.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
| 235 |
+
"model.layers.15.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 236 |
+
"model.layers.15.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
| 237 |
+
"model.layers.15.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 238 |
+
"model.layers.15.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
| 239 |
+
"model.layers.15.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 240 |
+
"model.layers.15.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
| 241 |
+
"model.layers.15.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 242 |
+
"model.layers.15.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
| 243 |
+
"model.layers.15.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 244 |
+
"model.layers.15.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 245 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 246 |
+
"model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 247 |
+
"model.layers.15.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 248 |
+
"model.layers.15.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 249 |
+
"model.layers.15.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 250 |
+
"model.layers.15.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 251 |
+
"model.layers.15.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 252 |
+
"model.layers.15.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
| 253 |
+
"model.layers.15.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 254 |
+
"model.layers.15.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 255 |
+
"model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 256 |
+
"model.layers.15.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 257 |
+
"model.layers.15.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 258 |
+
"model.layers.15.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 259 |
+
"model.layers.15.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 260 |
+
"model.layers.15.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 261 |
+
"model.layers.15.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 262 |
+
"model.layers.15.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 263 |
+
"model.layers.15.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 264 |
+
"model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 265 |
+
"model.layers.16.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 266 |
+
"model.layers.16.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
| 267 |
+
"model.layers.16.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 268 |
+
"model.layers.16.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
| 269 |
+
"model.layers.16.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 270 |
+
"model.layers.16.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
| 271 |
+
"model.layers.16.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 272 |
+
"model.layers.16.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
| 273 |
+
"model.layers.16.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 274 |
+
"model.layers.16.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
| 275 |
+
"model.layers.16.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 276 |
+
"model.layers.16.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 277 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 278 |
+
"model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 279 |
+
"model.layers.16.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 280 |
+
"model.layers.16.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 281 |
+
"model.layers.16.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 282 |
+
"model.layers.16.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 283 |
+
"model.layers.16.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 284 |
+
"model.layers.16.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
| 285 |
+
"model.layers.16.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 286 |
+
"model.layers.16.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 287 |
+
"model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 288 |
+
"model.layers.16.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 289 |
+
"model.layers.16.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 290 |
+
"model.layers.16.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 291 |
+
"model.layers.16.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 292 |
+
"model.layers.16.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 293 |
+
"model.layers.16.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 294 |
+
"model.layers.16.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 295 |
+
"model.layers.16.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 296 |
+
"model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 297 |
+
"model.layers.17.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 298 |
+
"model.layers.17.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
| 299 |
+
"model.layers.17.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 300 |
+
"model.layers.17.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
| 301 |
+
"model.layers.17.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 302 |
+
"model.layers.17.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
| 303 |
+
"model.layers.17.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 304 |
+
"model.layers.17.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
| 305 |
+
"model.layers.17.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 306 |
+
"model.layers.17.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
| 307 |
+
"model.layers.17.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 308 |
+
"model.layers.17.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 309 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 310 |
+
"model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 311 |
+
"model.layers.17.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 312 |
+
"model.layers.17.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 313 |
+
"model.layers.17.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 314 |
+
"model.layers.17.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 315 |
+
"model.layers.17.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 316 |
+
"model.layers.17.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
| 317 |
+
"model.layers.17.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 318 |
+
"model.layers.17.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 319 |
+
"model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 320 |
+
"model.layers.17.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 321 |
+
"model.layers.17.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 322 |
+
"model.layers.17.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 323 |
+
"model.layers.17.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 324 |
+
"model.layers.17.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 325 |
+
"model.layers.17.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 326 |
+
"model.layers.17.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 327 |
+
"model.layers.17.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 328 |
+
"model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 329 |
+
"model.layers.18.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 330 |
+
"model.layers.18.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
| 331 |
+
"model.layers.18.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 332 |
+
"model.layers.18.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
| 333 |
+
"model.layers.18.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 334 |
+
"model.layers.18.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
| 335 |
+
"model.layers.18.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 336 |
+
"model.layers.18.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
| 337 |
+
"model.layers.18.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 338 |
+
"model.layers.18.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
| 339 |
+
"model.layers.18.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 340 |
+
"model.layers.18.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 341 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 342 |
+
"model.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 343 |
+
"model.layers.18.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 344 |
+
"model.layers.18.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 345 |
+
"model.layers.18.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 346 |
+
"model.layers.18.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 347 |
+
"model.layers.18.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 348 |
+
"model.layers.18.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
| 349 |
+
"model.layers.18.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 350 |
+
"model.layers.18.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 351 |
+
"model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 352 |
+
"model.layers.18.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 353 |
+
"model.layers.18.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 354 |
+
"model.layers.18.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 355 |
+
"model.layers.18.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 356 |
+
"model.layers.18.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 357 |
+
"model.layers.18.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 358 |
+
"model.layers.18.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 359 |
+
"model.layers.18.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 360 |
+
"model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 361 |
+
"model.layers.19.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 362 |
+
"model.layers.19.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
| 363 |
+
"model.layers.19.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 364 |
+
"model.layers.19.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
| 365 |
+
"model.layers.19.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 366 |
+
"model.layers.19.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
| 367 |
+
"model.layers.19.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 368 |
+
"model.layers.19.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
| 369 |
+
"model.layers.19.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 370 |
+
"model.layers.19.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
| 371 |
+
"model.layers.19.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 372 |
+
"model.layers.19.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 373 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 374 |
+
"model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 375 |
+
"model.layers.19.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 376 |
+
"model.layers.19.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 377 |
+
"model.layers.19.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 378 |
+
"model.layers.19.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 379 |
+
"model.layers.19.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 380 |
+
"model.layers.19.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
| 381 |
+
"model.layers.19.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 382 |
+
"model.layers.19.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 383 |
+
"model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 384 |
+
"model.layers.19.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 385 |
+
"model.layers.19.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 386 |
+
"model.layers.19.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 387 |
+
"model.layers.19.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 388 |
+
"model.layers.19.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 389 |
+
"model.layers.19.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 390 |
+
"model.layers.19.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 391 |
+
"model.layers.19.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 392 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 393 |
+
"model.layers.2.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 394 |
+
"model.layers.2.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
| 395 |
+
"model.layers.2.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 396 |
+
"model.layers.2.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
| 397 |
+
"model.layers.2.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 398 |
+
"model.layers.2.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
| 399 |
+
"model.layers.2.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 400 |
+
"model.layers.2.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
| 401 |
+
"model.layers.2.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 402 |
+
"model.layers.2.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
| 403 |
+
"model.layers.2.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 404 |
+
"model.layers.2.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 405 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 406 |
+
"model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 407 |
+
"model.layers.2.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 408 |
+
"model.layers.2.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 409 |
+
"model.layers.2.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 410 |
+
"model.layers.2.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 411 |
+
"model.layers.2.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 412 |
+
"model.layers.2.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
| 413 |
+
"model.layers.2.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 414 |
+
"model.layers.2.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 415 |
+
"model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 416 |
+
"model.layers.2.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 417 |
+
"model.layers.2.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 418 |
+
"model.layers.2.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 419 |
+
"model.layers.2.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 420 |
+
"model.layers.2.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 421 |
+
"model.layers.2.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 422 |
+
"model.layers.2.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 423 |
+
"model.layers.2.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 424 |
+
"model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 425 |
+
"model.layers.20.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 426 |
+
"model.layers.20.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
| 427 |
+
"model.layers.20.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 428 |
+
"model.layers.20.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
| 429 |
+
"model.layers.20.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 430 |
+
"model.layers.20.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
| 431 |
+
"model.layers.20.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 432 |
+
"model.layers.20.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
| 433 |
+
"model.layers.20.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 434 |
+
"model.layers.20.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
| 435 |
+
"model.layers.20.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 436 |
+
"model.layers.20.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 437 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 438 |
+
"model.layers.20.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 439 |
+
"model.layers.20.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 440 |
+
"model.layers.20.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 441 |
+
"model.layers.20.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 442 |
+
"model.layers.20.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 443 |
+
"model.layers.20.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 444 |
+
"model.layers.20.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
| 445 |
+
"model.layers.20.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 446 |
+
"model.layers.20.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 447 |
+
"model.layers.20.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 448 |
+
"model.layers.20.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 449 |
+
"model.layers.20.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 450 |
+
"model.layers.20.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 451 |
+
"model.layers.20.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 452 |
+
"model.layers.20.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 453 |
+
"model.layers.20.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 454 |
+
"model.layers.20.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 455 |
+
"model.layers.20.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 456 |
+
"model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 457 |
+
"model.layers.21.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 458 |
+
"model.layers.21.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
| 459 |
+
"model.layers.21.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 460 |
+
"model.layers.21.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
| 461 |
+
"model.layers.21.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 462 |
+
"model.layers.21.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
| 463 |
+
"model.layers.21.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 464 |
+
"model.layers.21.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
| 465 |
+
"model.layers.21.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 466 |
+
"model.layers.21.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
| 467 |
+
"model.layers.21.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 468 |
+
"model.layers.21.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 469 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 470 |
+
"model.layers.21.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 471 |
+
"model.layers.21.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 472 |
+
"model.layers.21.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 473 |
+
"model.layers.21.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 474 |
+
"model.layers.21.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 475 |
+
"model.layers.21.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 476 |
+
"model.layers.21.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
| 477 |
+
"model.layers.21.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 478 |
+
"model.layers.21.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 479 |
+
"model.layers.21.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 480 |
+
"model.layers.21.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 481 |
+
"model.layers.21.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 482 |
+
"model.layers.21.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 483 |
+
"model.layers.21.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 484 |
+
"model.layers.21.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 485 |
+
"model.layers.21.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 486 |
+
"model.layers.21.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 487 |
+
"model.layers.21.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 488 |
+
"model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 489 |
+
"model.layers.22.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 490 |
+
"model.layers.22.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
| 491 |
+
"model.layers.22.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 492 |
+
"model.layers.22.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
| 493 |
+
"model.layers.22.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 494 |
+
"model.layers.22.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
| 495 |
+
"model.layers.22.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 496 |
+
"model.layers.22.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
| 497 |
+
"model.layers.22.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 498 |
+
"model.layers.22.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
| 499 |
+
"model.layers.22.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 500 |
+
"model.layers.22.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 501 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 502 |
+
"model.layers.22.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 503 |
+
"model.layers.22.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 504 |
+
"model.layers.22.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 505 |
+
"model.layers.22.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 506 |
+
"model.layers.22.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 507 |
+
"model.layers.22.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 508 |
+
"model.layers.22.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
| 509 |
+
"model.layers.22.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 510 |
+
"model.layers.22.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 511 |
+
"model.layers.22.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 512 |
+
"model.layers.22.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 513 |
+
"model.layers.22.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 514 |
+
"model.layers.22.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 515 |
+
"model.layers.22.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 516 |
+
"model.layers.22.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 517 |
+
"model.layers.22.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 518 |
+
"model.layers.22.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 519 |
+
"model.layers.22.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 520 |
+
"model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 521 |
+
"model.layers.23.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 522 |
+
"model.layers.23.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
| 523 |
+
"model.layers.23.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 524 |
+
"model.layers.23.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
| 525 |
+
"model.layers.23.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 526 |
+
"model.layers.23.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
| 527 |
+
"model.layers.23.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 528 |
+
"model.layers.23.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
| 529 |
+
"model.layers.23.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 530 |
+
"model.layers.23.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
| 531 |
+
"model.layers.23.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 532 |
+
"model.layers.23.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 533 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 534 |
+
"model.layers.23.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 535 |
+
"model.layers.23.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 536 |
+
"model.layers.23.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 537 |
+
"model.layers.23.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 538 |
+
"model.layers.23.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 539 |
+
"model.layers.23.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 540 |
+
"model.layers.23.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
| 541 |
+
"model.layers.23.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 542 |
+
"model.layers.23.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 543 |
+
"model.layers.23.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 544 |
+
"model.layers.23.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 545 |
+
"model.layers.23.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 546 |
+
"model.layers.23.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 547 |
+
"model.layers.23.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 548 |
+
"model.layers.23.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 549 |
+
"model.layers.23.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 550 |
+
"model.layers.23.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 551 |
+
"model.layers.23.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 552 |
+
"model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 553 |
+
"model.layers.24.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 554 |
+
"model.layers.24.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
| 555 |
+
"model.layers.24.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 556 |
+
"model.layers.24.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
| 557 |
+
"model.layers.24.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 558 |
+
"model.layers.24.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
| 559 |
+
"model.layers.24.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 560 |
+
"model.layers.24.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
| 561 |
+
"model.layers.24.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 562 |
+
"model.layers.24.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
| 563 |
+
"model.layers.24.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 564 |
+
"model.layers.24.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 565 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 566 |
+
"model.layers.24.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 567 |
+
"model.layers.24.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 568 |
+
"model.layers.24.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 569 |
+
"model.layers.24.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 570 |
+
"model.layers.24.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 571 |
+
"model.layers.24.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 572 |
+
"model.layers.24.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
| 573 |
+
"model.layers.24.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 574 |
+
"model.layers.24.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 575 |
+
"model.layers.24.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 576 |
+
"model.layers.24.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 577 |
+
"model.layers.24.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 578 |
+
"model.layers.24.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 579 |
+
"model.layers.24.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 580 |
+
"model.layers.24.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 581 |
+
"model.layers.24.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 582 |
+
"model.layers.24.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 583 |
+
"model.layers.24.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 584 |
+
"model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 585 |
+
"model.layers.25.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 586 |
+
"model.layers.25.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
| 587 |
+
"model.layers.25.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 588 |
+
"model.layers.25.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
| 589 |
+
"model.layers.25.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 590 |
+
"model.layers.25.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
| 591 |
+
"model.layers.25.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 592 |
+
"model.layers.25.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
| 593 |
+
"model.layers.25.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 594 |
+
"model.layers.25.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
| 595 |
+
"model.layers.25.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 596 |
+
"model.layers.25.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 597 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 598 |
+
"model.layers.25.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 599 |
+
"model.layers.25.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 600 |
+
"model.layers.25.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 601 |
+
"model.layers.25.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 602 |
+
"model.layers.25.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 603 |
+
"model.layers.25.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 604 |
+
"model.layers.25.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
| 605 |
+
"model.layers.25.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 606 |
+
"model.layers.25.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 607 |
+
"model.layers.25.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 608 |
+
"model.layers.25.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 609 |
+
"model.layers.25.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 610 |
+
"model.layers.25.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 611 |
+
"model.layers.25.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 612 |
+
"model.layers.25.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 613 |
+
"model.layers.25.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 614 |
+
"model.layers.25.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 615 |
+
"model.layers.25.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 616 |
+
"model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 617 |
+
"model.layers.26.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 618 |
+
"model.layers.26.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
| 619 |
+
"model.layers.26.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 620 |
+
"model.layers.26.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
| 621 |
+
"model.layers.26.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 622 |
+
"model.layers.26.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
| 623 |
+
"model.layers.26.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 624 |
+
"model.layers.26.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
| 625 |
+
"model.layers.26.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 626 |
+
"model.layers.26.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
| 627 |
+
"model.layers.26.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 628 |
+
"model.layers.26.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 629 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 630 |
+
"model.layers.26.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 631 |
+
"model.layers.26.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 632 |
+
"model.layers.26.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 633 |
+
"model.layers.26.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 634 |
+
"model.layers.26.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 635 |
+
"model.layers.26.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 636 |
+
"model.layers.26.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
| 637 |
+
"model.layers.26.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 638 |
+
"model.layers.26.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 639 |
+
"model.layers.26.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 640 |
+
"model.layers.26.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 641 |
+
"model.layers.26.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 642 |
+
"model.layers.26.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 643 |
+
"model.layers.26.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 644 |
+
"model.layers.26.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 645 |
+
"model.layers.26.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 646 |
+
"model.layers.26.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 647 |
+
"model.layers.26.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 648 |
+
"model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 649 |
+
"model.layers.27.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors",
|
| 650 |
+
"model.layers.27.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
|
| 651 |
+
"model.layers.27.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 652 |
+
"model.layers.27.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
|
| 653 |
+
"model.layers.27.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors",
|
| 654 |
+
"model.layers.27.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
|
| 655 |
+
"model.layers.27.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 656 |
+
"model.layers.27.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
|
| 657 |
+
"model.layers.27.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors",
|
| 658 |
+
"model.layers.27.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
|
| 659 |
+
"model.layers.27.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 660 |
+
"model.layers.27.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
|
| 661 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 662 |
+
"model.layers.27.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 663 |
+
"model.layers.27.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 664 |
+
"model.layers.27.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 665 |
+
"model.layers.27.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 666 |
+
"model.layers.27.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 667 |
+
"model.layers.27.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 668 |
+
"model.layers.27.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
| 669 |
+
"model.layers.27.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 670 |
+
"model.layers.27.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 671 |
+
"model.layers.27.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 672 |
+
"model.layers.27.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 673 |
+
"model.layers.27.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 674 |
+
"model.layers.27.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 675 |
+
"model.layers.27.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 676 |
+
"model.layers.27.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 677 |
+
"model.layers.27.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 678 |
+
"model.layers.27.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 679 |
+
"model.layers.27.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 680 |
+
"model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 681 |
+
"model.layers.28.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors",
|
| 682 |
+
"model.layers.28.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
|
| 683 |
+
"model.layers.28.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 684 |
+
"model.layers.28.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
|
| 685 |
+
"model.layers.28.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors",
|
| 686 |
+
"model.layers.28.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
|
| 687 |
+
"model.layers.28.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 688 |
+
"model.layers.28.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
|
| 689 |
+
"model.layers.28.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors",
|
| 690 |
+
"model.layers.28.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
|
| 691 |
+
"model.layers.28.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 692 |
+
"model.layers.28.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
|
| 693 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 694 |
+
"model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 695 |
+
"model.layers.28.self_attn.k_proj.g_idx": "model-00002-of-00002.safetensors",
|
| 696 |
+
"model.layers.28.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
|
| 697 |
+
"model.layers.28.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 698 |
+
"model.layers.28.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
|
| 699 |
+
"model.layers.28.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors",
|
| 700 |
+
"model.layers.28.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
|
| 701 |
+
"model.layers.28.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 702 |
+
"model.layers.28.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
|
| 703 |
+
"model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 704 |
+
"model.layers.28.self_attn.q_proj.g_idx": "model-00002-of-00002.safetensors",
|
| 705 |
+
"model.layers.28.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
|
| 706 |
+
"model.layers.28.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 707 |
+
"model.layers.28.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
|
| 708 |
+
"model.layers.28.self_attn.v_proj.g_idx": "model-00002-of-00002.safetensors",
|
| 709 |
+
"model.layers.28.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
|
| 710 |
+
"model.layers.28.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 711 |
+
"model.layers.28.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
|
| 712 |
+
"model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 713 |
+
"model.layers.29.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors",
|
| 714 |
+
"model.layers.29.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
|
| 715 |
+
"model.layers.29.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 716 |
+
"model.layers.29.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
|
| 717 |
+
"model.layers.29.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors",
|
| 718 |
+
"model.layers.29.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
|
| 719 |
+
"model.layers.29.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 720 |
+
"model.layers.29.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
|
| 721 |
+
"model.layers.29.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors",
|
| 722 |
+
"model.layers.29.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
|
| 723 |
+
"model.layers.29.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 724 |
+
"model.layers.29.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
|
| 725 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 726 |
+
"model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 727 |
+
"model.layers.29.self_attn.k_proj.g_idx": "model-00002-of-00002.safetensors",
|
| 728 |
+
"model.layers.29.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
|
| 729 |
+
"model.layers.29.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 730 |
+
"model.layers.29.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
|
| 731 |
+
"model.layers.29.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors",
|
| 732 |
+
"model.layers.29.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
|
| 733 |
+
"model.layers.29.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 734 |
+
"model.layers.29.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
|
| 735 |
+
"model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 736 |
+
"model.layers.29.self_attn.q_proj.g_idx": "model-00002-of-00002.safetensors",
|
| 737 |
+
"model.layers.29.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
|
| 738 |
+
"model.layers.29.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 739 |
+
"model.layers.29.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
|
| 740 |
+
"model.layers.29.self_attn.v_proj.g_idx": "model-00002-of-00002.safetensors",
|
| 741 |
+
"model.layers.29.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
|
| 742 |
+
"model.layers.29.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 743 |
+
"model.layers.29.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
|
| 744 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 745 |
+
"model.layers.3.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 746 |
+
"model.layers.3.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
| 747 |
+
"model.layers.3.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 748 |
+
"model.layers.3.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
| 749 |
+
"model.layers.3.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 750 |
+
"model.layers.3.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
| 751 |
+
"model.layers.3.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 752 |
+
"model.layers.3.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
| 753 |
+
"model.layers.3.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 754 |
+
"model.layers.3.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
| 755 |
+
"model.layers.3.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 756 |
+
"model.layers.3.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 757 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 758 |
+
"model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 759 |
+
"model.layers.3.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 760 |
+
"model.layers.3.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 761 |
+
"model.layers.3.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 762 |
+
"model.layers.3.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 763 |
+
"model.layers.3.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 764 |
+
"model.layers.3.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
| 765 |
+
"model.layers.3.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 766 |
+
"model.layers.3.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 767 |
+
"model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 768 |
+
"model.layers.3.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 769 |
+
"model.layers.3.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 770 |
+
"model.layers.3.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 771 |
+
"model.layers.3.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 772 |
+
"model.layers.3.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 773 |
+
"model.layers.3.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 774 |
+
"model.layers.3.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 775 |
+
"model.layers.3.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 776 |
+
"model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 777 |
+
"model.layers.30.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors",
|
| 778 |
+
"model.layers.30.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
|
| 779 |
+
"model.layers.30.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 780 |
+
"model.layers.30.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
|
| 781 |
+
"model.layers.30.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors",
|
| 782 |
+
"model.layers.30.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
|
| 783 |
+
"model.layers.30.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 784 |
+
"model.layers.30.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
|
| 785 |
+
"model.layers.30.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors",
|
| 786 |
+
"model.layers.30.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
|
| 787 |
+
"model.layers.30.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 788 |
+
"model.layers.30.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
|
| 789 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 790 |
+
"model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 791 |
+
"model.layers.30.self_attn.k_proj.g_idx": "model-00002-of-00002.safetensors",
|
| 792 |
+
"model.layers.30.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
|
| 793 |
+
"model.layers.30.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 794 |
+
"model.layers.30.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
|
| 795 |
+
"model.layers.30.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors",
|
| 796 |
+
"model.layers.30.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
|
| 797 |
+
"model.layers.30.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 798 |
+
"model.layers.30.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
|
| 799 |
+
"model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 800 |
+
"model.layers.30.self_attn.q_proj.g_idx": "model-00002-of-00002.safetensors",
|
| 801 |
+
"model.layers.30.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
|
| 802 |
+
"model.layers.30.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 803 |
+
"model.layers.30.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
|
| 804 |
+
"model.layers.30.self_attn.v_proj.g_idx": "model-00002-of-00002.safetensors",
|
| 805 |
+
"model.layers.30.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
|
| 806 |
+
"model.layers.30.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 807 |
+
"model.layers.30.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
|
| 808 |
+
"model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 809 |
+
"model.layers.31.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors",
|
| 810 |
+
"model.layers.31.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
|
| 811 |
+
"model.layers.31.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 812 |
+
"model.layers.31.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
|
| 813 |
+
"model.layers.31.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors",
|
| 814 |
+
"model.layers.31.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
|
| 815 |
+
"model.layers.31.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 816 |
+
"model.layers.31.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
|
| 817 |
+
"model.layers.31.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors",
|
| 818 |
+
"model.layers.31.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
|
| 819 |
+
"model.layers.31.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 820 |
+
"model.layers.31.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
|
| 821 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 822 |
+
"model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 823 |
+
"model.layers.31.self_attn.k_proj.g_idx": "model-00002-of-00002.safetensors",
|
| 824 |
+
"model.layers.31.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
|
| 825 |
+
"model.layers.31.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 826 |
+
"model.layers.31.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
|
| 827 |
+
"model.layers.31.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors",
|
| 828 |
+
"model.layers.31.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
|
| 829 |
+
"model.layers.31.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 830 |
+
"model.layers.31.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
|
| 831 |
+
"model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 832 |
+
"model.layers.31.self_attn.q_proj.g_idx": "model-00002-of-00002.safetensors",
|
| 833 |
+
"model.layers.31.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
|
| 834 |
+
"model.layers.31.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 835 |
+
"model.layers.31.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
|
| 836 |
+
"model.layers.31.self_attn.v_proj.g_idx": "model-00002-of-00002.safetensors",
|
| 837 |
+
"model.layers.31.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
|
| 838 |
+
"model.layers.31.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 839 |
+
"model.layers.31.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
|
| 840 |
+
"model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 841 |
+
"model.layers.32.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors",
|
| 842 |
+
"model.layers.32.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
|
| 843 |
+
"model.layers.32.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 844 |
+
"model.layers.32.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
|
| 845 |
+
"model.layers.32.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors",
|
| 846 |
+
"model.layers.32.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
|
| 847 |
+
"model.layers.32.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 848 |
+
"model.layers.32.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
|
| 849 |
+
"model.layers.32.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors",
|
| 850 |
+
"model.layers.32.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
|
| 851 |
+
"model.layers.32.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 852 |
+
"model.layers.32.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
|
| 853 |
+
"model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 854 |
+
"model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 855 |
+
"model.layers.32.self_attn.k_proj.g_idx": "model-00002-of-00002.safetensors",
|
| 856 |
+
"model.layers.32.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
|
| 857 |
+
"model.layers.32.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 858 |
+
"model.layers.32.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
|
| 859 |
+
"model.layers.32.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors",
|
| 860 |
+
"model.layers.32.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
|
| 861 |
+
"model.layers.32.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 862 |
+
"model.layers.32.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
|
| 863 |
+
"model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 864 |
+
"model.layers.32.self_attn.q_proj.g_idx": "model-00002-of-00002.safetensors",
|
| 865 |
+
"model.layers.32.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
|
| 866 |
+
"model.layers.32.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 867 |
+
"model.layers.32.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
|
| 868 |
+
"model.layers.32.self_attn.v_proj.g_idx": "model-00002-of-00002.safetensors",
|
| 869 |
+
"model.layers.32.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
|
| 870 |
+
"model.layers.32.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 871 |
+
"model.layers.32.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
|
| 872 |
+
"model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 873 |
+
"model.layers.33.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors",
|
| 874 |
+
"model.layers.33.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
|
| 875 |
+
"model.layers.33.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 876 |
+
"model.layers.33.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
|
| 877 |
+
"model.layers.33.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors",
|
| 878 |
+
"model.layers.33.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
|
| 879 |
+
"model.layers.33.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 880 |
+
"model.layers.33.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
|
| 881 |
+
"model.layers.33.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors",
|
| 882 |
+
"model.layers.33.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
|
| 883 |
+
"model.layers.33.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 884 |
+
"model.layers.33.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
|
| 885 |
+
"model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 886 |
+
"model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 887 |
+
"model.layers.33.self_attn.k_proj.g_idx": "model-00002-of-00002.safetensors",
|
| 888 |
+
"model.layers.33.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
|
| 889 |
+
"model.layers.33.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 890 |
+
"model.layers.33.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
|
| 891 |
+
"model.layers.33.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors",
|
| 892 |
+
"model.layers.33.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
|
| 893 |
+
"model.layers.33.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 894 |
+
"model.layers.33.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
|
| 895 |
+
"model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 896 |
+
"model.layers.33.self_attn.q_proj.g_idx": "model-00002-of-00002.safetensors",
|
| 897 |
+
"model.layers.33.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
|
| 898 |
+
"model.layers.33.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 899 |
+
"model.layers.33.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
|
| 900 |
+
"model.layers.33.self_attn.v_proj.g_idx": "model-00002-of-00002.safetensors",
|
| 901 |
+
"model.layers.33.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
|
| 902 |
+
"model.layers.33.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 903 |
+
"model.layers.33.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
|
| 904 |
+
"model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 905 |
+
"model.layers.34.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors",
|
| 906 |
+
"model.layers.34.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
|
| 907 |
+
"model.layers.34.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 908 |
+
"model.layers.34.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
|
| 909 |
+
"model.layers.34.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors",
|
| 910 |
+
"model.layers.34.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
|
| 911 |
+
"model.layers.34.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 912 |
+
"model.layers.34.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
|
| 913 |
+
"model.layers.34.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors",
|
| 914 |
+
"model.layers.34.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
|
| 915 |
+
"model.layers.34.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 916 |
+
"model.layers.34.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
|
| 917 |
+
"model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 918 |
+
"model.layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 919 |
+
"model.layers.34.self_attn.k_proj.g_idx": "model-00002-of-00002.safetensors",
|
| 920 |
+
"model.layers.34.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
|
| 921 |
+
"model.layers.34.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 922 |
+
"model.layers.34.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
|
| 923 |
+
"model.layers.34.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors",
|
| 924 |
+
"model.layers.34.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
|
| 925 |
+
"model.layers.34.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 926 |
+
"model.layers.34.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
|
| 927 |
+
"model.layers.34.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 928 |
+
"model.layers.34.self_attn.q_proj.g_idx": "model-00002-of-00002.safetensors",
|
| 929 |
+
"model.layers.34.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
|
| 930 |
+
"model.layers.34.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 931 |
+
"model.layers.34.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
|
| 932 |
+
"model.layers.34.self_attn.v_proj.g_idx": "model-00002-of-00002.safetensors",
|
| 933 |
+
"model.layers.34.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
|
| 934 |
+
"model.layers.34.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 935 |
+
"model.layers.34.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
|
| 936 |
+
"model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 937 |
+
"model.layers.35.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors",
|
| 938 |
+
"model.layers.35.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
|
| 939 |
+
"model.layers.35.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 940 |
+
"model.layers.35.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
|
| 941 |
+
"model.layers.35.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors",
|
| 942 |
+
"model.layers.35.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
|
| 943 |
+
"model.layers.35.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 944 |
+
"model.layers.35.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
|
| 945 |
+
"model.layers.35.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors",
|
| 946 |
+
"model.layers.35.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
|
| 947 |
+
"model.layers.35.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 948 |
+
"model.layers.35.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
|
| 949 |
+
"model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 950 |
+
"model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 951 |
+
"model.layers.35.self_attn.k_proj.g_idx": "model-00002-of-00002.safetensors",
|
| 952 |
+
"model.layers.35.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
|
| 953 |
+
"model.layers.35.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 954 |
+
"model.layers.35.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
|
| 955 |
+
"model.layers.35.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors",
|
| 956 |
+
"model.layers.35.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
|
| 957 |
+
"model.layers.35.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 958 |
+
"model.layers.35.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
|
| 959 |
+
"model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 960 |
+
"model.layers.35.self_attn.q_proj.g_idx": "model-00002-of-00002.safetensors",
|
| 961 |
+
"model.layers.35.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
|
| 962 |
+
"model.layers.35.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 963 |
+
"model.layers.35.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
|
| 964 |
+
"model.layers.35.self_attn.v_proj.g_idx": "model-00002-of-00002.safetensors",
|
| 965 |
+
"model.layers.35.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
|
| 966 |
+
"model.layers.35.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 967 |
+
"model.layers.35.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
|
| 968 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 969 |
+
"model.layers.4.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 970 |
+
"model.layers.4.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
| 971 |
+
"model.layers.4.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 972 |
+
"model.layers.4.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
| 973 |
+
"model.layers.4.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 974 |
+
"model.layers.4.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
| 975 |
+
"model.layers.4.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 976 |
+
"model.layers.4.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
| 977 |
+
"model.layers.4.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 978 |
+
"model.layers.4.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
| 979 |
+
"model.layers.4.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 980 |
+
"model.layers.4.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 981 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 982 |
+
"model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 983 |
+
"model.layers.4.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 984 |
+
"model.layers.4.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 985 |
+
"model.layers.4.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 986 |
+
"model.layers.4.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 987 |
+
"model.layers.4.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 988 |
+
"model.layers.4.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
| 989 |
+
"model.layers.4.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 990 |
+
"model.layers.4.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 991 |
+
"model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 992 |
+
"model.layers.4.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 993 |
+
"model.layers.4.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 994 |
+
"model.layers.4.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 995 |
+
"model.layers.4.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 996 |
+
"model.layers.4.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 997 |
+
"model.layers.4.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 998 |
+
"model.layers.4.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 999 |
+
"model.layers.4.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 1000 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 1001 |
+
"model.layers.5.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 1002 |
+
"model.layers.5.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
| 1003 |
+
"model.layers.5.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 1004 |
+
"model.layers.5.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
| 1005 |
+
"model.layers.5.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 1006 |
+
"model.layers.5.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
| 1007 |
+
"model.layers.5.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 1008 |
+
"model.layers.5.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
| 1009 |
+
"model.layers.5.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 1010 |
+
"model.layers.5.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
| 1011 |
+
"model.layers.5.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 1012 |
+
"model.layers.5.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 1013 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 1014 |
+
"model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 1015 |
+
"model.layers.5.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 1016 |
+
"model.layers.5.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 1017 |
+
"model.layers.5.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 1018 |
+
"model.layers.5.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 1019 |
+
"model.layers.5.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 1020 |
+
"model.layers.5.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
| 1021 |
+
"model.layers.5.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 1022 |
+
"model.layers.5.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 1023 |
+
"model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 1024 |
+
"model.layers.5.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 1025 |
+
"model.layers.5.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 1026 |
+
"model.layers.5.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 1027 |
+
"model.layers.5.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 1028 |
+
"model.layers.5.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 1029 |
+
"model.layers.5.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 1030 |
+
"model.layers.5.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 1031 |
+
"model.layers.5.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 1032 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 1033 |
+
"model.layers.6.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 1034 |
+
"model.layers.6.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
| 1035 |
+
"model.layers.6.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 1036 |
+
"model.layers.6.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
| 1037 |
+
"model.layers.6.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 1038 |
+
"model.layers.6.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
| 1039 |
+
"model.layers.6.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 1040 |
+
"model.layers.6.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
| 1041 |
+
"model.layers.6.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 1042 |
+
"model.layers.6.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
| 1043 |
+
"model.layers.6.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 1044 |
+
"model.layers.6.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 1045 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 1046 |
+
"model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 1047 |
+
"model.layers.6.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 1048 |
+
"model.layers.6.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 1049 |
+
"model.layers.6.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 1050 |
+
"model.layers.6.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 1051 |
+
"model.layers.6.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 1052 |
+
"model.layers.6.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
| 1053 |
+
"model.layers.6.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 1054 |
+
"model.layers.6.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 1055 |
+
"model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 1056 |
+
"model.layers.6.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 1057 |
+
"model.layers.6.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 1058 |
+
"model.layers.6.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 1059 |
+
"model.layers.6.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 1060 |
+
"model.layers.6.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 1061 |
+
"model.layers.6.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 1062 |
+
"model.layers.6.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 1063 |
+
"model.layers.6.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 1064 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 1065 |
+
"model.layers.7.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 1066 |
+
"model.layers.7.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
| 1067 |
+
"model.layers.7.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 1068 |
+
"model.layers.7.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
| 1069 |
+
"model.layers.7.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 1070 |
+
"model.layers.7.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
| 1071 |
+
"model.layers.7.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 1072 |
+
"model.layers.7.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
| 1073 |
+
"model.layers.7.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 1074 |
+
"model.layers.7.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
| 1075 |
+
"model.layers.7.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 1076 |
+
"model.layers.7.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 1077 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 1078 |
+
"model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 1079 |
+
"model.layers.7.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 1080 |
+
"model.layers.7.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 1081 |
+
"model.layers.7.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 1082 |
+
"model.layers.7.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 1083 |
+
"model.layers.7.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 1084 |
+
"model.layers.7.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
| 1085 |
+
"model.layers.7.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 1086 |
+
"model.layers.7.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 1087 |
+
"model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 1088 |
+
"model.layers.7.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 1089 |
+
"model.layers.7.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 1090 |
+
"model.layers.7.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 1091 |
+
"model.layers.7.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 1092 |
+
"model.layers.7.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 1093 |
+
"model.layers.7.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 1094 |
+
"model.layers.7.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 1095 |
+
"model.layers.7.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 1096 |
+
"model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 1097 |
+
"model.layers.8.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 1098 |
+
"model.layers.8.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
| 1099 |
+
"model.layers.8.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 1100 |
+
"model.layers.8.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
| 1101 |
+
"model.layers.8.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 1102 |
+
"model.layers.8.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
| 1103 |
+
"model.layers.8.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 1104 |
+
"model.layers.8.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
| 1105 |
+
"model.layers.8.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 1106 |
+
"model.layers.8.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
| 1107 |
+
"model.layers.8.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 1108 |
+
"model.layers.8.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 1109 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 1110 |
+
"model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 1111 |
+
"model.layers.8.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 1112 |
+
"model.layers.8.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 1113 |
+
"model.layers.8.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 1114 |
+
"model.layers.8.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 1115 |
+
"model.layers.8.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 1116 |
+
"model.layers.8.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
| 1117 |
+
"model.layers.8.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 1118 |
+
"model.layers.8.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 1119 |
+
"model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 1120 |
+
"model.layers.8.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 1121 |
+
"model.layers.8.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 1122 |
+
"model.layers.8.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 1123 |
+
"model.layers.8.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 1124 |
+
"model.layers.8.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 1125 |
+
"model.layers.8.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 1126 |
+
"model.layers.8.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 1127 |
+
"model.layers.8.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 1128 |
+
"model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 1129 |
+
"model.layers.9.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 1130 |
+
"model.layers.9.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
| 1131 |
+
"model.layers.9.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 1132 |
+
"model.layers.9.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
| 1133 |
+
"model.layers.9.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 1134 |
+
"model.layers.9.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
| 1135 |
+
"model.layers.9.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 1136 |
+
"model.layers.9.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
| 1137 |
+
"model.layers.9.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 1138 |
+
"model.layers.9.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
| 1139 |
+
"model.layers.9.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 1140 |
+
"model.layers.9.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 1141 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 1142 |
+
"model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 1143 |
+
"model.layers.9.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 1144 |
+
"model.layers.9.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 1145 |
+
"model.layers.9.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 1146 |
+
"model.layers.9.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 1147 |
+
"model.layers.9.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 1148 |
+
"model.layers.9.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
| 1149 |
+
"model.layers.9.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 1150 |
+
"model.layers.9.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 1151 |
+
"model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 1152 |
+
"model.layers.9.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 1153 |
+
"model.layers.9.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 1154 |
+
"model.layers.9.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 1155 |
+
"model.layers.9.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 1156 |
+
"model.layers.9.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 1157 |
+
"model.layers.9.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 1158 |
+
"model.layers.9.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 1159 |
+
"model.layers.9.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 1160 |
+
"model.norm.weight": "model-00002-of-00002.safetensors"
|
| 1161 |
+
}
|
| 1162 |
+
}
|
quant_log.csv
ADDED
|
@@ -0,0 +1,253 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
layer,module,loss,samples,damp,time
|
| 2 |
+
0,self_attn.k_proj,0.0000000015,0.01000,1.712
|
| 3 |
+
0,self_attn.v_proj,0.0000000012,0.01000,0.925
|
| 4 |
+
0,self_attn.q_proj,0.0000000049,0.01000,0.904
|
| 5 |
+
0,self_attn.o_proj,0.0000000163,0.01000,0.882
|
| 6 |
+
0,mlp.up_proj,0.0000005740,0.01000,0.911
|
| 7 |
+
0,mlp.gate_proj,0.0000006532,0.01000,0.902
|
| 8 |
+
0,mlp.down_proj,0.0000001969,0.01000,3.010
|
| 9 |
+
1,self_attn.k_proj,0.0000000043,0.01000,0.906
|
| 10 |
+
1,self_attn.v_proj,0.0000000045,0.01000,0.888
|
| 11 |
+
1,self_attn.q_proj,0.0000000146,0.01000,0.913
|
| 12 |
+
1,self_attn.o_proj,0.0000000275,0.01000,0.908
|
| 13 |
+
1,mlp.up_proj,0.0000052082,0.01000,0.939
|
| 14 |
+
1,mlp.gate_proj,0.0000131845,0.01000,0.924
|
| 15 |
+
1,mlp.down_proj,0.0000001877,0.01000,3.054
|
| 16 |
+
2,self_attn.k_proj,0.0000000112,0.01000,0.878
|
| 17 |
+
2,self_attn.v_proj,0.0000000108,0.01000,0.871
|
| 18 |
+
2,self_attn.q_proj,0.0000000380,0.01000,0.874
|
| 19 |
+
2,self_attn.o_proj,0.0000000328,0.01000,0.881
|
| 20 |
+
2,mlp.up_proj,0.0000202890,0.01000,0.915
|
| 21 |
+
2,mlp.gate_proj,0.0000263211,0.01000,0.912
|
| 22 |
+
2,mlp.down_proj,0.0000001653,0.01000,3.074
|
| 23 |
+
3,self_attn.k_proj,0.0000000193,0.01000,0.885
|
| 24 |
+
3,self_attn.v_proj,0.0000000196,0.01000,0.870
|
| 25 |
+
3,self_attn.q_proj,0.0000000692,0.01000,0.886
|
| 26 |
+
3,self_attn.o_proj,0.0000000536,0.01000,0.885
|
| 27 |
+
3,mlp.up_proj,0.0000122846,0.01000,0.917
|
| 28 |
+
3,mlp.gate_proj,0.0000268380,0.01000,0.910
|
| 29 |
+
3,mlp.down_proj,0.0000004506,0.01000,3.076
|
| 30 |
+
4,self_attn.k_proj,0.0000000434,0.01000,0.890
|
| 31 |
+
4,self_attn.v_proj,0.0000000442,0.01000,0.867
|
| 32 |
+
4,self_attn.q_proj,0.0000001510,0.01000,0.881
|
| 33 |
+
4,self_attn.o_proj,0.0000000948,0.01000,0.883
|
| 34 |
+
4,mlp.up_proj,0.0000121759,0.01000,0.916
|
| 35 |
+
4,mlp.gate_proj,0.0000322729,0.01000,0.909
|
| 36 |
+
4,mlp.down_proj,0.0000008796,0.01000,3.055
|
| 37 |
+
5,self_attn.k_proj,0.0000000433,0.01000,0.896
|
| 38 |
+
5,self_attn.v_proj,0.0000000457,0.01000,0.875
|
| 39 |
+
5,self_attn.q_proj,0.0000001578,0.01000,0.884
|
| 40 |
+
5,self_attn.o_proj,0.0000001365,0.01000,0.903
|
| 41 |
+
5,mlp.up_proj,0.0000080894,0.01000,0.927
|
| 42 |
+
5,mlp.gate_proj,0.0000179048,0.01000,0.915
|
| 43 |
+
5,mlp.down_proj,0.0000013001,0.01000,3.052
|
| 44 |
+
6,self_attn.k_proj,0.0000000803,0.01000,0.905
|
| 45 |
+
6,self_attn.v_proj,0.0000000884,0.01000,0.899
|
| 46 |
+
6,self_attn.q_proj,0.0000003184,0.01000,0.897
|
| 47 |
+
6,self_attn.o_proj,0.0000003676,0.01000,0.900
|
| 48 |
+
6,mlp.up_proj,0.0000104167,0.01000,0.969
|
| 49 |
+
6,mlp.gate_proj,0.0000199433,0.01000,0.937
|
| 50 |
+
6,mlp.down_proj,0.0001922736,0.01000,3.135
|
| 51 |
+
7,self_attn.k_proj,0.0000001980,0.01000,0.901
|
| 52 |
+
7,self_attn.v_proj,0.0000001892,0.01000,0.869
|
| 53 |
+
7,self_attn.q_proj,0.0000006958,0.01000,0.908
|
| 54 |
+
7,self_attn.o_proj,0.0000003350,0.01000,0.886
|
| 55 |
+
7,mlp.up_proj,0.0000127284,0.01000,0.918
|
| 56 |
+
7,mlp.gate_proj,0.0000226174,0.01000,0.961
|
| 57 |
+
7,mlp.down_proj,0.0000018001,0.01000,3.109
|
| 58 |
+
8,self_attn.k_proj,0.0000003166,0.01000,0.902
|
| 59 |
+
8,self_attn.v_proj,0.0000003271,0.01000,0.889
|
| 60 |
+
8,self_attn.q_proj,0.0000011330,0.01000,0.884
|
| 61 |
+
8,self_attn.o_proj,0.0000005447,0.01000,0.886
|
| 62 |
+
8,mlp.up_proj,0.0000123870,0.01000,0.920
|
| 63 |
+
8,mlp.gate_proj,0.0000142148,0.01000,0.908
|
| 64 |
+
8,mlp.down_proj,0.0000031396,0.01000,3.126
|
| 65 |
+
9,self_attn.k_proj,0.0000004336,0.01000,0.904
|
| 66 |
+
9,self_attn.v_proj,0.0000003877,0.01000,0.886
|
| 67 |
+
9,self_attn.q_proj,0.0000014913,0.01000,0.897
|
| 68 |
+
9,self_attn.o_proj,0.0000006713,0.01000,0.904
|
| 69 |
+
9,mlp.up_proj,0.0000159213,0.01000,0.936
|
| 70 |
+
9,mlp.gate_proj,0.0000215900,0.01000,0.928
|
| 71 |
+
9,mlp.down_proj,0.0000036478,0.01000,3.164
|
| 72 |
+
10,self_attn.k_proj,0.0000007654,0.01000,0.947
|
| 73 |
+
10,self_attn.v_proj,0.0000008362,0.01000,0.891
|
| 74 |
+
10,self_attn.q_proj,0.0000027566,0.01000,0.931
|
| 75 |
+
10,self_attn.o_proj,0.0000010241,0.01000,0.932
|
| 76 |
+
10,mlp.up_proj,0.0000156613,0.01000,0.940
|
| 77 |
+
10,mlp.gate_proj,0.0000200901,0.01000,0.928
|
| 78 |
+
10,mlp.down_proj,0.0000037414,0.01000,3.141
|
| 79 |
+
11,self_attn.k_proj,0.0000003988,0.01000,0.888
|
| 80 |
+
11,self_attn.v_proj,0.0000003882,0.01000,0.876
|
| 81 |
+
11,self_attn.q_proj,0.0000013864,0.01000,0.878
|
| 82 |
+
11,self_attn.o_proj,0.0000008979,0.01000,0.894
|
| 83 |
+
11,mlp.up_proj,0.0000157748,0.01000,0.921
|
| 84 |
+
11,mlp.gate_proj,0.0000185915,0.01000,0.910
|
| 85 |
+
11,mlp.down_proj,0.0000037746,0.01000,3.063
|
| 86 |
+
12,self_attn.k_proj,0.0000004513,0.01000,0.886
|
| 87 |
+
12,self_attn.v_proj,0.0000004669,0.01000,0.875
|
| 88 |
+
12,self_attn.q_proj,0.0000015881,0.01000,0.911
|
| 89 |
+
12,self_attn.o_proj,0.0000010671,0.01000,0.884
|
| 90 |
+
12,mlp.up_proj,0.0000165085,0.01000,0.920
|
| 91 |
+
12,mlp.gate_proj,0.0000181187,0.01000,0.920
|
| 92 |
+
12,mlp.down_proj,0.0000039800,0.01000,3.168
|
| 93 |
+
13,self_attn.k_proj,0.0000003635,0.01000,0.885
|
| 94 |
+
13,self_attn.v_proj,0.0000003458,0.01000,0.869
|
| 95 |
+
13,self_attn.q_proj,0.0000013292,0.01000,0.887
|
| 96 |
+
13,self_attn.o_proj,0.0000007286,0.01000,0.885
|
| 97 |
+
13,mlp.up_proj,0.0000171527,0.01000,0.919
|
| 98 |
+
13,mlp.gate_proj,0.0000174607,0.01000,0.912
|
| 99 |
+
13,mlp.down_proj,0.0000045170,0.01000,2.989
|
| 100 |
+
14,self_attn.k_proj,0.0000006080,0.01000,0.885
|
| 101 |
+
14,self_attn.v_proj,0.0000006287,0.01000,0.869
|
| 102 |
+
14,self_attn.q_proj,0.0000022256,0.01000,0.874
|
| 103 |
+
14,self_attn.o_proj,0.0000014882,0.01000,0.883
|
| 104 |
+
14,mlp.up_proj,0.0000173904,0.01000,0.955
|
| 105 |
+
14,mlp.gate_proj,0.0000175352,0.01000,0.913
|
| 106 |
+
14,mlp.down_proj,0.0000043650,0.01000,3.159
|
| 107 |
+
15,self_attn.k_proj,0.0000006405,0.01000,0.895
|
| 108 |
+
15,self_attn.v_proj,0.0000006059,0.01000,0.872
|
| 109 |
+
15,self_attn.q_proj,0.0000022680,0.01000,0.889
|
| 110 |
+
15,self_attn.o_proj,0.0000010979,0.01000,0.885
|
| 111 |
+
15,mlp.up_proj,0.0000170070,0.01000,0.919
|
| 112 |
+
15,mlp.gate_proj,0.0000164598,0.01000,0.914
|
| 113 |
+
15,mlp.down_proj,0.0000044099,0.01000,3.104
|
| 114 |
+
16,self_attn.k_proj,0.0000010972,0.01000,0.891
|
| 115 |
+
16,self_attn.v_proj,0.0000012423,0.01000,0.879
|
| 116 |
+
16,self_attn.q_proj,0.0000042154,0.01000,0.882
|
| 117 |
+
16,self_attn.o_proj,0.0000014473,0.01000,0.901
|
| 118 |
+
16,mlp.up_proj,0.0000186370,0.01000,0.926
|
| 119 |
+
16,mlp.gate_proj,0.0000186707,0.01000,0.912
|
| 120 |
+
16,mlp.down_proj,0.0000095448,0.01000,3.062
|
| 121 |
+
17,self_attn.k_proj,0.0000010145,0.01000,0.890
|
| 122 |
+
17,self_attn.v_proj,0.0000011109,0.01000,0.885
|
| 123 |
+
17,self_attn.q_proj,0.0000040763,0.01000,0.883
|
| 124 |
+
17,self_attn.o_proj,0.0000016497,0.01000,0.920
|
| 125 |
+
17,mlp.up_proj,0.0000180247,0.01000,0.921
|
| 126 |
+
17,mlp.gate_proj,0.0000175535,0.01000,0.915
|
| 127 |
+
17,mlp.down_proj,0.0000056334,0.01000,3.068
|
| 128 |
+
18,self_attn.k_proj,0.0000011954,0.01000,0.886
|
| 129 |
+
18,self_attn.v_proj,0.0000012692,0.01000,0.873
|
| 130 |
+
18,self_attn.q_proj,0.0000045311,0.01000,0.887
|
| 131 |
+
18,self_attn.o_proj,0.0000019605,0.01000,0.890
|
| 132 |
+
18,mlp.up_proj,0.0000205253,0.01000,0.920
|
| 133 |
+
18,mlp.gate_proj,0.0000200017,0.01000,0.919
|
| 134 |
+
18,mlp.down_proj,0.0000065850,0.01000,3.093
|
| 135 |
+
19,self_attn.k_proj,0.0000023365,0.01000,0.903
|
| 136 |
+
19,self_attn.v_proj,0.0000024214,0.01000,0.891
|
| 137 |
+
19,self_attn.q_proj,0.0000092070,0.01000,0.905
|
| 138 |
+
19,self_attn.o_proj,0.0000029968,0.01000,0.906
|
| 139 |
+
19,mlp.up_proj,0.0000228412,0.01000,0.938
|
| 140 |
+
19,mlp.gate_proj,0.0000218078,0.01000,0.930
|
| 141 |
+
19,mlp.down_proj,0.0000084889,0.01000,3.115
|
| 142 |
+
20,self_attn.k_proj,0.0000020128,0.01000,0.905
|
| 143 |
+
20,self_attn.v_proj,0.0000022445,0.01000,0.890
|
| 144 |
+
20,self_attn.q_proj,0.0000085190,0.01000,0.901
|
| 145 |
+
20,self_attn.o_proj,0.0000028852,0.01000,0.905
|
| 146 |
+
20,mlp.up_proj,0.0000252495,0.01000,0.918
|
| 147 |
+
20,mlp.gate_proj,0.0000236520,0.01000,0.908
|
| 148 |
+
20,mlp.down_proj,0.0000100402,0.01000,3.059
|
| 149 |
+
21,self_attn.k_proj,0.0000027516,0.01000,0.893
|
| 150 |
+
21,self_attn.v_proj,0.0000032758,0.01000,0.875
|
| 151 |
+
21,self_attn.q_proj,0.0000112753,0.01000,0.885
|
| 152 |
+
21,self_attn.o_proj,0.0000033707,0.01000,0.911
|
| 153 |
+
21,mlp.up_proj,0.0000297586,0.01000,0.940
|
| 154 |
+
21,mlp.gate_proj,0.0000277278,0.01000,0.935
|
| 155 |
+
21,mlp.down_proj,0.0000132390,0.01000,3.054
|
| 156 |
+
22,self_attn.k_proj,0.0000062124,0.01000,0.899
|
| 157 |
+
22,self_attn.v_proj,0.0000065444,0.01000,0.876
|
| 158 |
+
22,self_attn.q_proj,0.0000241311,0.01000,0.885
|
| 159 |
+
22,self_attn.o_proj,0.0000067822,0.01000,0.898
|
| 160 |
+
22,mlp.up_proj,0.0000342028,0.01000,0.931
|
| 161 |
+
22,mlp.gate_proj,0.0000322704,0.01000,0.915
|
| 162 |
+
22,mlp.down_proj,0.0000216577,0.01000,3.156
|
| 163 |
+
23,self_attn.k_proj,0.0000061361,0.01000,0.893
|
| 164 |
+
23,self_attn.v_proj,0.0000074565,0.01000,0.877
|
| 165 |
+
23,self_attn.q_proj,0.0000253022,0.01000,0.890
|
| 166 |
+
23,self_attn.o_proj,0.0000105262,0.01000,0.907
|
| 167 |
+
23,mlp.up_proj,0.0000393763,0.01000,0.937
|
| 168 |
+
23,mlp.gate_proj,0.0000381544,0.01000,0.920
|
| 169 |
+
23,mlp.down_proj,0.0000307144,0.01000,3.058
|
| 170 |
+
24,self_attn.k_proj,0.0000111583,0.01000,0.886
|
| 171 |
+
24,self_attn.v_proj,0.0000144551,0.01000,0.882
|
| 172 |
+
24,self_attn.q_proj,0.0000454749,0.01000,0.881
|
| 173 |
+
24,self_attn.o_proj,0.0000115710,0.01000,0.888
|
| 174 |
+
24,mlp.up_proj,0.0000445548,0.01000,0.925
|
| 175 |
+
24,mlp.gate_proj,0.0000436983,0.01000,0.921
|
| 176 |
+
24,mlp.down_proj,0.0000383308,0.01000,3.064
|
| 177 |
+
25,self_attn.k_proj,0.0000089802,0.01000,0.929
|
| 178 |
+
25,self_attn.v_proj,0.0000106912,0.01000,0.883
|
| 179 |
+
25,self_attn.q_proj,0.0000350779,0.01000,0.883
|
| 180 |
+
25,self_attn.o_proj,0.0000077190,0.01000,0.895
|
| 181 |
+
25,mlp.up_proj,0.0000516038,0.01000,0.919
|
| 182 |
+
25,mlp.gate_proj,0.0000512468,0.01000,0.922
|
| 183 |
+
25,mlp.down_proj,0.0000478184,0.01000,3.053
|
| 184 |
+
26,self_attn.k_proj,0.0000148602,0.01000,0.888
|
| 185 |
+
26,self_attn.v_proj,0.0000182355,0.01000,0.872
|
| 186 |
+
26,self_attn.q_proj,0.0000605304,0.01000,0.891
|
| 187 |
+
26,self_attn.o_proj,0.0000092113,0.01000,0.893
|
| 188 |
+
26,mlp.up_proj,0.0000635605,0.01000,0.922
|
| 189 |
+
26,mlp.gate_proj,0.0000621471,0.01000,0.953
|
| 190 |
+
26,mlp.down_proj,0.0000573816,0.01000,3.140
|
| 191 |
+
27,self_attn.k_proj,0.0000167369,0.01000,0.894
|
| 192 |
+
27,self_attn.v_proj,0.0000221709,0.01000,0.875
|
| 193 |
+
27,self_attn.q_proj,0.0000698549,0.01000,0.890
|
| 194 |
+
27,self_attn.o_proj,0.0000105676,0.01000,0.896
|
| 195 |
+
27,mlp.up_proj,0.0000737238,0.01000,0.923
|
| 196 |
+
27,mlp.gate_proj,0.0000708008,0.01000,0.917
|
| 197 |
+
27,mlp.down_proj,0.0000797470,0.01000,3.123
|
| 198 |
+
28,self_attn.k_proj,0.0000194154,0.01000,0.890
|
| 199 |
+
28,self_attn.v_proj,0.0000222215,0.01000,0.879
|
| 200 |
+
28,self_attn.q_proj,0.0000736696,0.01000,0.886
|
| 201 |
+
28,self_attn.o_proj,0.0000162227,0.01000,0.888
|
| 202 |
+
28,mlp.up_proj,0.0000866654,0.01000,0.921
|
| 203 |
+
28,mlp.gate_proj,0.0000811015,0.01000,0.913
|
| 204 |
+
28,mlp.down_proj,0.0001118279,0.01000,3.063
|
| 205 |
+
29,self_attn.k_proj,0.0000441453,0.01000,0.904
|
| 206 |
+
29,self_attn.v_proj,0.0000646906,0.01000,0.876
|
| 207 |
+
29,self_attn.q_proj,0.0001756297,0.01000,0.882
|
| 208 |
+
29,self_attn.o_proj,0.0000162280,0.01000,0.892
|
| 209 |
+
29,mlp.up_proj,0.0001036480,0.01000,0.931
|
| 210 |
+
29,mlp.gate_proj,0.0000942627,0.01000,0.924
|
| 211 |
+
29,mlp.down_proj,0.0001289722,0.01000,3.069
|
| 212 |
+
30,self_attn.k_proj,0.0000534550,0.01000,0.894
|
| 213 |
+
30,self_attn.v_proj,0.0000700705,0.01000,0.872
|
| 214 |
+
30,self_attn.q_proj,0.0002013896,0.01000,0.881
|
| 215 |
+
30,self_attn.o_proj,0.0000261334,0.01000,0.895
|
| 216 |
+
30,mlp.up_proj,0.0001134598,0.01000,0.931
|
| 217 |
+
30,mlp.gate_proj,0.0001007077,0.01000,0.915
|
| 218 |
+
30,mlp.down_proj,0.0001700256,0.01000,3.058
|
| 219 |
+
31,self_attn.k_proj,0.0000754044,0.01000,0.894
|
| 220 |
+
31,self_attn.v_proj,0.0001038457,0.01000,0.885
|
| 221 |
+
31,self_attn.q_proj,0.0002635791,0.01000,0.893
|
| 222 |
+
31,self_attn.o_proj,0.0000305994,0.01000,0.901
|
| 223 |
+
31,mlp.up_proj,0.0001222418,0.01000,0.931
|
| 224 |
+
31,mlp.gate_proj,0.0001049834,0.01000,0.918
|
| 225 |
+
31,mlp.down_proj,0.0002177585,0.01000,3.056
|
| 226 |
+
32,self_attn.k_proj,0.0001011146,0.01000,0.890
|
| 227 |
+
32,self_attn.v_proj,0.0001517884,0.01000,0.882
|
| 228 |
+
32,self_attn.q_proj,0.0003828967,0.01000,0.891
|
| 229 |
+
32,self_attn.o_proj,0.0000431652,0.01000,0.904
|
| 230 |
+
32,mlp.up_proj,0.0001302504,0.01000,0.928
|
| 231 |
+
32,mlp.gate_proj,0.0001096425,0.01000,0.925
|
| 232 |
+
32,mlp.down_proj,0.0002804651,0.01000,3.047
|
| 233 |
+
33,self_attn.k_proj,0.0001741775,0.01000,0.892
|
| 234 |
+
33,self_attn.v_proj,0.0003288537,0.01000,0.878
|
| 235 |
+
33,self_attn.q_proj,0.0007499020,0.01000,0.897
|
| 236 |
+
33,self_attn.o_proj,0.0000649437,0.01000,0.896
|
| 237 |
+
33,mlp.up_proj,0.0001392706,0.01000,0.924
|
| 238 |
+
33,mlp.gate_proj,0.0001153356,0.01000,0.922
|
| 239 |
+
33,mlp.down_proj,0.0003548277,0.01000,3.062
|
| 240 |
+
34,self_attn.k_proj,0.0001468701,0.01000,0.890
|
| 241 |
+
34,self_attn.v_proj,0.0002285834,0.01000,0.875
|
| 242 |
+
34,self_attn.q_proj,0.0006159075,0.01000,0.894
|
| 243 |
+
34,self_attn.o_proj,0.0001155951,0.01000,0.894
|
| 244 |
+
34,mlp.up_proj,0.0001467356,0.01000,0.921
|
| 245 |
+
34,mlp.gate_proj,0.0001274698,0.01000,0.916
|
| 246 |
+
34,mlp.down_proj,0.0004528920,0.01000,3.020
|
| 247 |
+
35,self_attn.k_proj,0.0000713502,0.01000,0.897
|
| 248 |
+
35,self_attn.v_proj,0.0000922083,0.01000,0.875
|
| 249 |
+
35,self_attn.q_proj,0.0002660156,0.01000,0.889
|
| 250 |
+
35,self_attn.o_proj,0.0000814533,0.01000,0.904
|
| 251 |
+
35,mlp.up_proj,0.0001837838,0.01000,0.938
|
| 252 |
+
35,mlp.gate_proj,0.0001648423,0.01000,0.911
|
| 253 |
+
35,mlp.down_proj,0.0008856815,0.01000,3.072
|
quantize_config.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bits": 4,
|
| 3 |
+
"group_size": 128,
|
| 4 |
+
"desc_act": true,
|
| 5 |
+
"sym": true,
|
| 6 |
+
"lm_head": false,
|
| 7 |
+
"quant_method": "gptq",
|
| 8 |
+
"checkpoint_format": "gptq",
|
| 9 |
+
"pack_dtype": "int32",
|
| 10 |
+
"meta": {
|
| 11 |
+
"quantizer": [
|
| 12 |
+
"gptqmodel:3.0.0-dev"
|
| 13 |
+
],
|
| 14 |
+
"uri": "https://github.com/modelcloud/gptqmodel",
|
| 15 |
+
"damp_percent": 0.01,
|
| 16 |
+
"damp_auto_increment": 0.0025,
|
| 17 |
+
"static_groups": false,
|
| 18 |
+
"true_sequential": true,
|
| 19 |
+
"mse": 0.0,
|
| 20 |
+
"v2": false,
|
| 21 |
+
"v2_alpha": 0.25
|
| 22 |
+
}
|
| 23 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|object_ref_start|>",
|
| 6 |
+
"<|object_ref_end|>",
|
| 7 |
+
"<|box_start|>",
|
| 8 |
+
"<|box_end|>",
|
| 9 |
+
"<|quad_start|>",
|
| 10 |
+
"<|quad_end|>",
|
| 11 |
+
"<|vision_start|>",
|
| 12 |
+
"<|vision_end|>",
|
| 13 |
+
"<|vision_pad|>",
|
| 14 |
+
"<|image_pad|>",
|
| 15 |
+
"<|video_pad|>"
|
| 16 |
+
],
|
| 17 |
+
"eos_token": {
|
| 18 |
+
"content": "<|im_end|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
"pad_token": "<|vision_pad|>"
|
| 25 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
|
| 3 |
+
size 11422654
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,241 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"151643": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"151644": {
|
| 14 |
+
"content": "<|im_start|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"151645": {
|
| 22 |
+
"content": "<|im_end|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"151646": {
|
| 30 |
+
"content": "<|object_ref_start|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"151647": {
|
| 38 |
+
"content": "<|object_ref_end|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"151648": {
|
| 46 |
+
"content": "<|box_start|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"151649": {
|
| 54 |
+
"content": "<|box_end|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"151650": {
|
| 62 |
+
"content": "<|quad_start|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"151651": {
|
| 70 |
+
"content": "<|quad_end|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"151652": {
|
| 78 |
+
"content": "<|vision_start|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"151653": {
|
| 86 |
+
"content": "<|vision_end|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"151654": {
|
| 94 |
+
"content": "<|vision_pad|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"151655": {
|
| 102 |
+
"content": "<|image_pad|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"151656": {
|
| 110 |
+
"content": "<|video_pad|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"151657": {
|
| 118 |
+
"content": "<tool_call>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"151658": {
|
| 126 |
+
"content": "</tool_call>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"151659": {
|
| 134 |
+
"content": "<|fim_prefix|>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"151660": {
|
| 142 |
+
"content": "<|fim_middle|>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"151661": {
|
| 150 |
+
"content": "<|fim_suffix|>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"151662": {
|
| 158 |
+
"content": "<|fim_pad|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"151663": {
|
| 166 |
+
"content": "<|repo_name|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"151664": {
|
| 174 |
+
"content": "<|file_sep|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
},
|
| 181 |
+
"151665": {
|
| 182 |
+
"content": "<tool_response>",
|
| 183 |
+
"lstrip": false,
|
| 184 |
+
"normalized": false,
|
| 185 |
+
"rstrip": false,
|
| 186 |
+
"single_word": false,
|
| 187 |
+
"special": false
|
| 188 |
+
},
|
| 189 |
+
"151666": {
|
| 190 |
+
"content": "</tool_response>",
|
| 191 |
+
"lstrip": false,
|
| 192 |
+
"normalized": false,
|
| 193 |
+
"rstrip": false,
|
| 194 |
+
"single_word": false,
|
| 195 |
+
"special": false
|
| 196 |
+
},
|
| 197 |
+
"151667": {
|
| 198 |
+
"content": "<think>",
|
| 199 |
+
"lstrip": false,
|
| 200 |
+
"normalized": false,
|
| 201 |
+
"rstrip": false,
|
| 202 |
+
"single_word": false,
|
| 203 |
+
"special": false
|
| 204 |
+
},
|
| 205 |
+
"151668": {
|
| 206 |
+
"content": "</think>",
|
| 207 |
+
"lstrip": false,
|
| 208 |
+
"normalized": false,
|
| 209 |
+
"rstrip": false,
|
| 210 |
+
"single_word": false,
|
| 211 |
+
"special": false
|
| 212 |
+
}
|
| 213 |
+
},
|
| 214 |
+
"additional_special_tokens": [
|
| 215 |
+
"<|im_start|>",
|
| 216 |
+
"<|im_end|>",
|
| 217 |
+
"<|object_ref_start|>",
|
| 218 |
+
"<|object_ref_end|>",
|
| 219 |
+
"<|box_start|>",
|
| 220 |
+
"<|box_end|>",
|
| 221 |
+
"<|quad_start|>",
|
| 222 |
+
"<|quad_end|>",
|
| 223 |
+
"<|vision_start|>",
|
| 224 |
+
"<|vision_end|>",
|
| 225 |
+
"<|vision_pad|>",
|
| 226 |
+
"<|image_pad|>",
|
| 227 |
+
"<|video_pad|>"
|
| 228 |
+
],
|
| 229 |
+
"bos_token": null,
|
| 230 |
+
"clean_up_tokenization_spaces": false,
|
| 231 |
+
"eos_token": "<|im_end|>",
|
| 232 |
+
"errors": "replace",
|
| 233 |
+
"extra_special_tokens": {},
|
| 234 |
+
"model_max_length": 40960,
|
| 235 |
+
"pad_token": "<|vision_pad|>",
|
| 236 |
+
"padding_side": "right",
|
| 237 |
+
"split_special_tokens": false,
|
| 238 |
+
"tokenizer_class": "Qwen2TokenizerFast",
|
| 239 |
+
"unk_token": null,
|
| 240 |
+
"_commit_hash": null
|
| 241 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|