Upload all model with 17 experts (12.0B params)

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,405 @@
+---
+license: apache-2.0
+datasets:
+  - AmanPriyanshu/GPT-OSS-20B-MoE-expert-activations
+language:
+  - en
+pipeline_tag: text-generation
+tags:
+  - mixture-of-experts
+  - moe
+  - expert-pruning
+  - gpt-oss
+  - openai
+  - reasoning
+  - all
+  - specialized
+  - efficient
+  - transformer
+  - causal-lm
+  - text-generation
+  - pytorch
+  - pruned-model
+  - domain-specific
+---
+
+# All GPT-OSS Model (17 Experts)
+
+**Project**: https://amanpriyanshu.github.io/GPT-OSS-MoE-ExpertFingerprinting/
+
+<div align="center">
+
+### 👥 Follow the Authors
+
+**Aman Priyanshu**
+[![LinkedIn](https://img.shields.io/badge/LinkedIn-0077B5?style=for-the-badge&logo=linkedin&logoColor=white)](https://www.linkedin.com/in/aman-priyanshu/)
+[![Twitter](https://img.shields.io/badge/Twitter-1DA1F2?style=for-the-badge&logo=twitter&logoColor=white)](https://x.com/AmanPriyanshu6)
+[![Website](https://img.shields.io/badge/Website-FF7139?style=for-the-badge&logo=firefox&logoColor=white)](https://amanpriyanshu.github.io/)
+
+**Supriti Vijay**
+[![LinkedIn](https://img.shields.io/badge/LinkedIn-0077B5?style=for-the-badge&logo=linkedin&logoColor=white)](https://www.linkedin.com/in/supriti-vijay/)
+[![Twitter](https://img.shields.io/badge/Twitter-1DA1F2?style=for-the-badge&logo=twitter&logoColor=white)](https://x.com/SupritiVijay)
+[![Website](https://img.shields.io/badge/Website-FF7139?style=for-the-badge&logo=firefox&logoColor=white)](https://supritivijay.github.io/)
+
+</div>
+
+## Introduction
+
+This is a pruned variant of OpenAI's GPT-OSS-20B model, reduced to 17 experts per layer based on activation patterns from the [AmanPriyanshu/GPT-OSS-20B MoE Expert Activations dataset](https://huggingface.co/datasets/AmanPriyanshu/GPT-OSS-20B-MoE-expert-activations). We analyzed router decisions across evaluation benchmarks to identify and retain experts most relevant for all tasks.
+
+**⚠️ Experimental Model**: This is an experimental pruned model that may not work well - check the [examples below](#model-examples) to see if the outputs meet your needs before use.
+
+This pruning approach reduces the model size while attempting to preserve performance on the target domain.
+
+## Model Architecture & Statistics
+
+| Metric | Value |
+|--------|-------|
+| **Base Model** | openai/gpt-oss-20b |
+| **Architecture** | Mixture-of-Experts Transformer |
+| **Total Parameters** | ~12.0B (pruned from 21B) |
+| **Original Experts per Layer** | 32 |
+| **Pruned Experts per Layer** | 17 |
+| **Layers** | 24 |
+| **Top-k Routing** | 4 |
+| **Context Length** | 128K tokens |
+| **Attention Heads** | 64 (Query), 8 (Key-Value) |
+| **Residual Dimension** | 2880 |
+| **Attention Pattern** | Alternating dense & sliding window (128 tokens) |
+| **Positional Encoding** | RoPE (Rotary Position Embedding) |
+| **Normalization** | RMSNorm |
+| **Precision** | BF16 |
+| **License** | Apache 2.0 |
+| **Specialization** | All |
+
+## Pruning Methodology
+
+### What is Expert Pruning?
+Mixture-of-Experts models contain multiple specialized sub-networks (experts) per layer. During inference, only a subset of experts are activated for each token. Expert pruning involves:
+
+1. **Analyzing Usage Patterns**: Tracking which experts activate most frequently for specific tasks
+2. **Removing Underutilized Experts**: Discarding experts with low activation rates for the target domain
+3. **Preserving Router Functionality**: Maintaining the routing mechanism with fewer available experts
+
+### Our Approach
+- **Data-Driven Selection**: Used activation patterns from all evaluation tasks
+- **Systematic Reduction**: Reduced from 32 to 17 experts per layer
+- **No Retraining**: Direct removal without additional training steps
+
+## Performance & Applications
+
+### Pruning Benefits
+- **Smaller Memory Footprint**: 53.1% of original expert parameters
+- **Reduced Computational Load**: Fewer routing decisions during inference
+- **Focused Capabilities**: Retains experts relevant to all tasks
+
+### Use Cases
+- **Speculative Decoding**: Draft model for full GPT-OSS-20B
+- **Resource-Constrained Deployment**: Edge devices, mobile applications
+- **Research**: Study expert specialization in MoE models
+- **Fine-tuning**: Smaller base model for domain adaptation
+
+*Note: Performance may vary depending on how well the pruned experts match your specific use case.*
+
+## Motivation & Expert Selection
+
+This general-purpose model maintains broad capabilities across all domains while significantly reducing computational requirements. It preserves the essential routing patterns discovered across our comprehensive analysis of diverse evaluation benchmarks including GPQA, MMLU, SORRY-Bench, and Tulu3 datasets.
+
+The expert selection process utilized our comprehensive analysis of router activation patterns across multiple evaluation benchmarks:
+
+- **GPQA**: Graduate-level questions in physics, chemistry, biology (Diamond & Expert subsets)
+- **MMLU/MMLU-Pro**: Comprehensive knowledge across 57+ subjects including science, medicine, law
+- **SORRY-Bench**: Safety evaluation across harmful content categories  
+- **Tulu3**: Persona-driven instruction following with verifiable constraints
+- **Polyglot-or-Not**: Multilingual factual completion tasks
+
+By identifying experts that consistently activated for all tasks, we created this specialized model that maintains domain expertise while significantly reducing computational requirements from 32 to 17 experts per layer.
+
+## Dataset & Analysis Foundation
+
+This model is based on analysis from the **GPT-OSS-20B MoE Expert Activations dataset** available at:
+🔗 **https://huggingface.co/datasets/AmanPriyanshu/GPT-OSS-20B-MoE-expert-activations**
+
+The dataset contains router activation patterns from OpenAI's GPT-OSS-20B model across diverse evaluation benchmarks, enabling the creation of these domain-optimized models through systematic expert pruning.
+
+### Pruning Methodology
+Our approach involves:
+1. **Activation Analysis**: Comprehensive evaluation of expert usage patterns across domain-specific tasks
+2. **Expert Ranking**: Identification of the most frequently activated experts for target domains  
+3. **Systematic Pruning**: Reduction from 32 to 17 experts while preserving router functionality
+4. **Quality Validation**: Testing to ensure maintained performance on target tasks
+
+*This is a direct pruning approach - no additional training was performed. The model inherits all capabilities from the original GPT-OSS-20B with focused expert selection.*
+
+## Usage
+
+### CPU Inference
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
+
+# Load the specialized model on CPU
+model = AutoModelForCausalLM.from_pretrained(
+    "AmanPriyanshu/gpt-oss-12.0b-specialized-all-pruned-moe-only-17-experts", 
+    torch_dtype=torch.bfloat16, 
+    device_map="cpu", 
+    trust_remote_code=True
+)
+tokenizer = AutoTokenizer.from_pretrained("AmanPriyanshu/gpt-oss-12.0b-specialized-all-pruned-moe-only-17-experts")
+
+# Generate with the model
+messages = [
+    {"role": "user", "content": "What is artificial intelligence and how does it work?"}
+]
+
+inputs = tokenizer.apply_chat_template(
+    messages, 
+    add_generation_prompt=True, 
+    return_tensors="pt", 
+    return_dict=True,
+    reasoning_effort="medium"
+)
+
+# Ensure inputs are on the same device as model
+inputs = {k: v.to(model.device) for k, v in inputs.items()}
+
+outputs = model.generate(
+    **inputs, 
+    max_new_tokens=512,
+    do_sample=True,
+    temperature=0.1,
+    top_p=0.9,
+    pad_token_id=tokenizer.eos_token_id,
+    eos_token_id=tokenizer.eos_token_id
+)
+
+# Decode only the generated part
+input_length = inputs['input_ids'].shape[1]
+response_tokens = outputs[0][input_length:]
+response = tokenizer.decode(response_tokens, skip_special_tokens=True)
+print(response)
+```
+
+### Apple Silicon (MPS) Inference
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
+
+# Check MPS availability and load model
+device = "mps" if torch.backends.mps.is_available() else "cpu"
+
+model = AutoModelForCausalLM.from_pretrained(
+    "AmanPriyanshu/gpt-oss-12.0b-specialized-all-pruned-moe-only-17-experts", 
+    torch_dtype=torch.float16,  # Better MPS compatibility
+    device_map=device, 
+    trust_remote_code=True,
+    low_cpu_mem_usage=True
+)
+tokenizer = AutoTokenizer.from_pretrained("AmanPriyanshu/gpt-oss-12.0b-specialized-all-pruned-moe-only-17-experts")
+
+# Generate with the model
+messages = [
+    {"role": "user", "content": "What is artificial intelligence and how does it work?"}
+]
+
+inputs = tokenizer.apply_chat_template(
+    messages, 
+    add_generation_prompt=True, 
+    return_tensors="pt", 
+    return_dict=True,
+    reasoning_effort="medium"
+)
+
+# Move inputs to model device
+inputs = {k: v.to(model.device) if isinstance(v, torch.Tensor) else v for k, v in inputs.items()}
+
+# Use torch.no_grad for MPS stability
+with torch.no_grad():
+    outputs = model.generate(
+        **inputs, 
+        max_new_tokens=512,
+        do_sample=True,
+        temperature=0.1,
+        top_p=0.9,
+        pad_token_id=tokenizer.eos_token_id,
+        eos_token_id=tokenizer.eos_token_id,
+        use_cache=True
+    )
+
+# Decode only the generated part
+input_length = inputs['input_ids'].shape[1]
+response_tokens = outputs[0][input_length:]
+response = tokenizer.decode(response_tokens, skip_special_tokens=True)
+print(response)
+```
+
+### GPU Inference
+
+For CUDA GPU inference, the models work with minimal modifications from the CPU example above. Simply change:
+```python
+device_map="auto"  # Will automatically use GPU if available
+torch_dtype=torch.bfloat16  # or torch.float16
+```
+
+## Model Examples
+
+The following examples demonstrate the model's performance on all tasks:
+
+### Example 1
+**Question:** What is artificial intelligence and how does it work?
+
+**Response:**
+```
+<|channel|>analysis<|message|>Need explain AI, basics, machine learning, models, data, algorithms.<|end|><|start|>assistant<|channel|>final<|message|>## 1.  What is Artificial Intelligence?
+
+Artificial Intelligence (AI) is a field of computer science that studies how to build machines (or software) that can perform tasks that are normally associated with human intelligence.  
+These tasks include:
+
+| Category | Typical Human Skill | Typical AI Skill |
+|---|---|---|
+| **Perception** | Seeing, hearing, reading | Image recognition, speech recognition, text parsing |
+| **Reasoning** | Solving puzzles, making decisions | Logical inference, probabilistic modeling |
+| **Learning** | Learning from experience | Machine‑learning algorithms that improve with data |
+| **Creativity** | Writing stories, composing music | Generative models that produce novel content |
+| **Interaction** | Talking, understanding context | Natural‑language processing, dialogue systems |
+
+AI is *not* a single technology; it is a collection of methods, models, and tools that let computers emulate or surpass human abilities in specific domains.
+
+---
+
+## 2.  How Does AI Work? – The Big Picture
+
+1. **Data** – The raw “experience” that the system learns from.  
+   *Examples*: images, audio clips, text, sensor readings, user actions.
+
+2. **Representation** – Convert raw data into a form that a computer can manipulate.  
+   *Examples*: pixel arrays → vectors, words → tokens, audio → frequency bands.
+
+3. **Model** – A mathematical structure that captures patterns in the data.  
+   *Examples*: neural networks, Bayesian models, reinforcement‑learning agents.
+
+4. **Training / Optimization** – Adjust the model’s internal parameters so that it predicts or produces the desired output.  
+   *Examples*: gradient descent, Monte‑Carlo sampling, policy learning.
+
+5. **Evaluation / Deployment** – Test the model on new data, refine it, and then use it in real applications.
+
+---
+
+## 3.  Core AI Techniques
+
+| Technique | What It Does | Typical Use Cases |
+|---|---|---|
+| **Classical Algorithms** (e.g., rule‑based, decision trees) | Encode explicit rules | Simple robotics, spreadsheet logic |
+| **Statistical Models** (e.g., Gaussian, Poisson) | Capture probability distributions | Spam filtering, weather prediction |
+| **Machine Learning (ML)** | Learn patterns from data | Image classification, recommendation systems |
+| **Deep Learning (
+```
+
+---
+
+### Example 2
+**Question:** Explain Einstein's theory of relativity in simple terms.
+
+**Response:**
+```
+<|channel|>analysis<|message|>Need simple explanation.<|end|><|start|>assistant<|channel|>final<|message|>**Einstein’s Theory of Relativity – in plain words**
+
+---
+
+### 1. Two parts of the theory
+
+| Part | What it says | Everyday picture |
+|------|--------------|-----------------|
+| **Galilean (Classical) Relativity** | “If you’re moving fast, you can’t see the motion of the world around you.” | Imagine you’re in a car that’s going 60 mph. Inside the car you feel at‑stand‑still, but you can see the street moving. If the car were going 120 mph, you’d still feel at‑stand‑still, but the street would look even faster. |
+| **Einstein’s Relativity (Two‑Part)** | 1. **Speed of Light is the same everywhere** (the “speed of light” is a universal constant). 2. **Time is a “moving” thing that depends on how fast you’re going relative to light.** | 1. Think of a light‑bulbul that always travels at the same speed, no matter where it starts. 2. If you’re moving very fast (close to the speed of light), the clock on your body will tick slower compared to a clock that’s standing still. |
+
+---
+
+### 2. The “speed of light” idea
+
+- Light travels at a fixed speed, about 300 000 km per second.  
+- Nothing can go faster than light (in the universe we know).  
+- Because light is the fastest, it becomes a natural “yardstick” for measuring distances and times.
+
+---
+
+### 3. Why time changes
+
+- **Relative speed matters**: If you’re moving close to the speed of light, the light you see from the outside is “compressed” – it takes longer for it to reach you.  
+- **Result**: Your own clock runs slower. This is called **“time dilation.”**  
+- **Example**: A spaceship that travels at 99 % of the speed of light for 10 years (on the ship) will return to Earth after about 10.5 Earth years. The crew aged 10 years, Earth people aged 10.5 years.
+
+---
+
+### 4. The “two‑world” view
+
+- **Our world**: We’re moving very slowly compared to light, so our clocks run normally.  
+- **A very fast world**: If something moves close
+```
+
+---
+
+### Example 3
+**Question:** How does democracy function in modern governments?
+
+**Response:**
+```
+<|channel|>analysis<|message|>Need explain democratic functions, institutions, processes, checks, representation, elections, rule of law.<|end|><|start|>assistant<|channel|>final<|message|>### 1.  What “democracy” means today  
+In contemporary politics “democracy” is not a single recipe but a set of **principles** that most modern governments try to embody:
+
+| Principle | Typical Institutional / Procedural Expression |
+|---|---|
+| **Popular sovereignty** | The people are the ultimate source of political authority. |
+| **Rule of law** | Laws are made, applied, and interpreted by independent institutions, not by a single ruler. |
+| **Political pluralism** | Multiple parties, interest groups, and viewpoints can compete for power. |
+| **Political participation** | Citizens can vote, run for office, petition, protest, and engage in public debate. |
+| **Political accountability** | Elected officials are answerable to the electorate and to the law. |
+| **Civil‑rights protection** | Freedom of speech, assembly, association, and equality before the law. |
+
+These principles are woven into the **constitutional architecture** of a state and into its **political culture**.
+
+---
+
+### 2.  Core institutions that make democracy work  
+
+| Institution | How it functions in a democratic system |
+|---|---|
+| **Constitution** | A written (or unwritten) charter that sets the limits of power, enumerates rights, and defines the separation of powers. |
+| **Legislature** | Elected representatives debate, draft, and pass laws. In most democrates it is bicameral (e.g., Parliament + Senate) or unicameral. |
+| **Executive** | The head of government (pres‑ or prime‑minister) implements laws, runs the state, and is accountable to the legislature. |
+| **Judiciary** | Independent courts interpret the constitution and laws, protecting minority rights and checking executive/legislative over‑reach. |
+| **Electoral System** | Regular, free, fair elections (often with secret ballots, independent electoral commissions, and transparent vote‑counting). |
+| **Political Parties & Parties System** | Organize voters, formulate platforms, and provide a mechanism for policy competition. |
+| **Civil Society & Media** | Watchdog, inform, mobilize, and hold officials accountable. |
+| **Checks & Balances** | Mechanisms (e.g., veto, judicial review, impeachment) that prevent any branch from dominating. |
+
+---
+
+###
+```
+
+---
+
+## Citation
+
+If you use this model in your research, please cite:
+
+```bibtex
+@misc{priyanshu2025gptoss,
+  title={{GPT-OSS MoE Expert Fingerprinting: Analyzing Expert Activation Patterns in Mixture of Experts Models}},
+  author={Priyanshu, Aman and Vijay, Supriti},
+  year={2025},
+  howpublished={\url{https://amanpriyanshu.github.io/GPT-OSS-MoE-ExpertFingerprinting/}},
+  note={Interactive analysis tool for expert activation patterns in MoE architectures}
+}
+```
+
+## References & Resources
+
+- **Original Model**: [OpenAI GPT-OSS Model Card](https://openai.com/index/introducing-gpt-oss/)
+- **Model Hub**: [GPT-OSS-20B on Hugging Face](https://huggingface.co/openai/gpt-oss-20b)
+- **Expert Analysis Dataset**: [GPT-OSS-20B MoE Expert Activations](https://huggingface.co/datasets/AmanPriyanshu/GPT-OSS-20B-MoE-expert-activations)
+- **Project Page**: [GPT-OSS MoE Expert Fingerprinting](https://amanpriyanshu.github.io/GPT-OSS-MoE-ExpertFingerprinting/)
+- **GitHub Repository**: [OpenAI GPT-OSS](https://github.com/openai/gpt-oss)

chat_template.jinja

@@ -0,0 +1,331 @@
+{#-
+  In addition to the normal inputs of `messages` and `tools`, this template also accepts the
+  following kwargs:
+  - "builtin_tools": A list, can contain "browser" and/or "python".
+  - "model_identity": A string that optionally describes the model identity.
+  - "reasoning_effort": A string that describes the reasoning effort, defaults to "medium".
+ #}
+
+{#- Tool Definition Rendering ============================================== #}
+{%- macro render_typescript_type(param_spec, required_params, is_nullable=false) -%}
+    {%- if param_spec.type == "array" -%}
+        {%- if param_spec['items'] -%}
+            {%- if param_spec['items']['type'] == "string" -%}
+                {{- "string[]" }}
+            {%- elif param_spec['items']['type'] == "number" -%}
+                {{- "number[]" }}
+            {%- elif param_spec['items']['type'] == "integer" -%}
+                {{- "number[]" }}
+            {%- elif param_spec['items']['type'] == "boolean" -%}
+                {{- "boolean[]" }}
+            {%- else -%}
+                {%- set inner_type = render_typescript_type(param_spec['items'], required_params) -%}
+                {%- if inner_type == "object | object" or inner_type|length > 50 -%}
+                    {{- "any[]" }}
+                {%- else -%}
+                    {{- inner_type + "[]" }}
+                {%- endif -%}
+            {%- endif -%}
+            {%- if param_spec.nullable -%}
+                {{- " | null" }}
+            {%- endif -%}
+        {%- else -%}
+            {{- "any[]" }}
+            {%- if param_spec.nullable -%}
+                {{- " | null" }}
+            {%- endif -%}
+        {%- endif -%}
+    {%- elif param_spec.type is defined and param_spec.type is iterable and param_spec.type is not string and param_spec.type is not mapping and param_spec.type[0] is defined -%}
+        {#- Handle array of types like ["object", "object"] from Union[dict, list] #}
+        {%- if param_spec.type | length > 1 -%}
+            {{- param_spec.type | join(" | ") }}
+        {%- else -%}
+            {{- param_spec.type[0] }}
+        {%- endif -%}
+    {%- elif param_spec.oneOf -%}
+        {#- Handle oneOf schemas - check for complex unions and fallback to any #}
+        {%- set has_object_variants = false -%}
+        {%- for variant in param_spec.oneOf -%}
+            {%- if variant.type == "object" -%}
+                {%- set has_object_variants = true -%}
+            {%- endif -%}
+        {%- endfor -%}
+        {%- if has_object_variants and param_spec.oneOf|length > 1 -%}
+            {{- "any" }}
+        {%- else -%}
+            {%- for variant in param_spec.oneOf -%}
+                {{- render_typescript_type(variant, required_params) -}}
+                {%- if variant.description %}
+                    {{- "// " + variant.description }}
+                {%- endif -%}
+                {%- if variant.default is defined %}
+                    {{ "// default: " + variant.default|tojson }}
+                {%- endif -%}
+                {%- if not loop.last %}
+                    {{- " | " }}
+                {% endif -%}
+            {%- endfor -%}
+        {%- endif -%}
+    {%- elif param_spec.type == "string" -%}
+        {%- if param_spec.enum -%}
+            {{- '"' + param_spec.enum|join('" | "') + '"' -}}
+        {%- else -%}
+            {{- "string" }}
+            {%- if param_spec.nullable %}
+                {{- " | null" }}
+            {%- endif -%}
+        {%- endif -%}
+    {%- elif param_spec.type == "number" -%}
+        {{- "number" }}
+    {%- elif param_spec.type == "integer" -%}
+        {{- "number" }}
+    {%- elif param_spec.type == "boolean" -%}
+        {{- "boolean" }}
+
+    {%- elif param_spec.type == "object" -%}
+        {%- if param_spec.properties -%}
+            {{- "{\n" }}
+            {%- for prop_name, prop_spec in param_spec.properties.items() -%}
+                {{- prop_name -}}
+                {%- if prop_name not in (param_spec.required or []) -%}
+                    {{- "?" }}
+                {%- endif -%}
+                {{- ": " }}
+                {{ render_typescript_type(prop_spec, param_spec.required or []) }}
+                {%- if not loop.last -%}
+                    {{-", " }}
+                {%- endif -%}
+            {%- endfor -%}
+            {{- "}" }}
+        {%- else -%}
+            {{- "object" }}
+        {%- endif -%}
+    {%- else -%}
+        {{- "any" }}
+    {%- endif -%}
+{%- endmacro -%}
+
+{%- macro render_tool_namespace(namespace_name, tools) -%}
+    {{- "## " + namespace_name + "\n\n" }}
+    {{- "namespace " + namespace_name + " {\n\n" }}
+    {%- for tool in tools %}
+        {%- set tool = tool.function %}
+        {{- "// " + tool.description + "\n" }}
+        {{- "type "+ tool.name + " = " }}
+        {%- if tool.parameters and tool.parameters.properties %}
+            {{- "(_: {\n" }}
+            {%- for param_name, param_spec in tool.parameters.properties.items() %}
+                {%- if param_spec.description %}
+                    {{- "// " + param_spec.description + "\n" }}
+                {%- endif %}
+                {{- param_name }}
+                {%- if param_name not in (tool.parameters.required or []) -%}
+                    {{- "?" }}
+                {%- endif -%}
+                {{- ": " }}
+                {{- render_typescript_type(param_spec, tool.parameters.required or []) }}
+                {%- if param_spec.default is defined -%}
+                    {%- if param_spec.enum %}
+                        {{- ", // default: " + param_spec.default }}
+                    {%- elif param_spec.oneOf %}
+                        {{- "// default: " + param_spec.default }}
+                    {%- else %}
+                        {{- ", // default: " + param_spec.default|tojson }}
+                    {%- endif -%}
+                {%- endif -%}
+                {%- if not loop.last %}
+                    {{- ",\n" }}
+                {%- else %}
+                    {{- ",\n" }}
+                {%- endif -%}
+            {%- endfor %}
+            {{- "}) => any;\n\n" }}
+        {%- else -%}
+            {{- "() => any;\n\n" }}
+        {%- endif -%}
+    {%- endfor %}
+    {{- "} // namespace " + namespace_name }}
+{%- endmacro -%}
+
+{%- macro render_builtin_tools(browser_tool, python_tool) -%}
+    {%- if browser_tool %}
+        {{- "## browser\n\n" }}
+        {{- "// Tool for browsing.\n" }}
+        {{- "// The `cursor` appears in brackets before each browsing display: `[{cursor}]`.\n" }}
+        {{- "// Cite information from the tool using the following format:\n" }}
+        {{- "// `【{cursor}†L{line_start}(-L{line_end})?】`, for example: `【6†L9-L11】` or `【8†L3】`.\n" }}
+        {{- "// Do not quote more than 10 words directly from the tool output.\n" }}
+        {{- "// sources=web (default: web)\n" }}
+        {{- "namespace browser {\n\n" }}
+        {{- "// Searches for information related to `query` and displays `topn` results.\n" }}
+        {{- "type search = (_: {\n" }}
+        {{- "query: string,\n" }}
+        {{- "topn?: number, // default: 10\n" }}
+        {{- "source?: string,\n" }}
+        {{- "}) => any;\n\n" }}
+        {{- "// Opens the link `id` from the page indicated by `cursor` starting at line number `loc`, showing `num_lines` lines.\n" }}
+        {{- "// Valid link ids are displayed with the formatting: `【{id}†.*】`.\n" }}
+        {{- "// If `cursor` is not provided, the most recent page is implied.\n" }}
+        {{- "// If `id` is a string, it is treated as a fully qualified URL associated with `source`.\n" }}
+        {{- "// If `loc` is not provided, the viewport will be positioned at the beginning of the document or centered on the most relevant passage, if available.\n" }}
+        {{- "// Use this function without `id` to scroll to a new location of an opened page.\n" }}
+        {{- "type open = (_: {\n" }}
+        {{- "id?: number | string, // default: -1\n" }}
+        {{- "cursor?: number, // default: -1\n" }}
+        {{- "loc?: number, // default: -1\n" }}
+        {{- "num_lines?: number, // default: -1\n" }}
+        {{- "view_source?: boolean, // default: false\n" }}
+        {{- "source?: string,\n" }}
+        {{- "}) => any;\n\n" }}
+        {{- "// Finds exact matches of `pattern` in the current page, or the page given by `cursor`.\n" }}
+        {{- "type find = (_: {\n" }}
+        {{- "pattern: string,\n" }}
+        {{- "cursor?: number, // default: -1\n" }}
+        {{- "}) => any;\n\n" }}
+        {{- "} // namespace browser\n\n" }}
+    {%- endif -%}
+
+    {%- if python_tool %}
+        {{- "## python\n\n" }}
+        {{- "Use this tool to execute Python code in your chain of thought. The code will not be shown to the user. This tool should be used for internal reasoning, but not for code that is intended to be visible to the user (e.g. when creating plots, tables, or files).\n\n" }}
+        {{- "When you send a message containing Python code to python, it will be executed in a stateful Jupyter notebook environment. python will respond with the output of the execution or time out after 120.0 seconds. The drive at '/mnt/data' can be used to save and persist user files. Internet access for this session is UNKNOWN. Depends on the cluster.\n\n" }}
+    {%- endif -%}
+{%- endmacro -%}
+
+{#- System Message Construction ============================================ #}
+{%- macro build_system_message() -%}
+    {%- if model_identity is not defined %}
+        {%- set model_identity = "You are ChatGPT, a large language model trained by OpenAI." %}
+    {%- endif %}
+    {{- model_identity + "\n" }}
+    {{- "Knowledge cutoff: 2024-06\n" }}
+    {{- "Current date: " + strftime_now("%Y-%m-%d") + "\n\n" }}
+    {%- if reasoning_effort is not defined %}
+        {%- set reasoning_effort = "medium" %}
+    {%- endif %}
+    {{- "Reasoning: " + reasoning_effort + "\n\n" }}
+    {%- if builtin_tools %}
+        {{- "# Tools\n\n" }}
+        {%- set available_builtin_tools = namespace(browser=false, python=false) %}
+        {%- for tool in builtin_tools %}
+            {%- if tool == "browser" %}
+                {%- set available_builtin_tools.browser = true %}
+            {%- elif tool == "python" %}
+                {%- set available_builtin_tools.python = true %}
+            {%- endif %}
+        {%- endfor %}
+        {{- render_builtin_tools(available_builtin_tools.browser, available_builtin_tools.python) }}
+    {%- endif -%}
+    {{- "# Valid channels: analysis, commentary, final. Channel must be included for every message." }}
+    {%- if tools -%}
+        {{- "\nCalls to these tools must go to the commentary channel: 'functions'." }}
+    {%- endif -%}
+{%- endmacro -%}
+
+{#- Main Template Logic ================================================= #}
+{#- Set defaults #}
+
+{#- Render system message #}
+{{- "<|start|>system<|message|>" }}
+{{- build_system_message() }}
+{{- "<|end|>" }}
+
+{#- Extract developer message #}
+{%- if messages[0].role == "developer" or messages[0].role == "system" %}
+    {%- set developer_message = messages[0].content %}
+    {%- set loop_messages = messages[1:] %}
+{%- else %}
+    {%- set developer_message = "" %}
+    {%- set loop_messages = messages %}
+{%- endif %}
+
+{#- Render developer message #}
+{%- if developer_message or tools %}
+    {{- "<|start|>developer<|message|>" }}
+    {%- if developer_message %}
+        {{- "# Instructions\n\n" }}
+        {{- developer_message }}
+        {{- "\n\n" }}
+    {%- endif %}
+    {%- if tools -%}
+        {{- "# Tools\n\n" }}
+        {{- render_tool_namespace("functions", tools) }}
+    {%- endif -%}
+    {{- "<|end|>" }}
+{%- endif %}
+
+{#- Render messages #}
+{%- set last_tool_call = namespace(name=none) %}
+{%- for message in loop_messages -%}
+    {#- At this point only assistant/user/tool messages should remain #}
+    {%- if message.role == 'assistant' -%}
+        {#- Checks to ensure the messages are being passed in the format we expect #}
+        {%- if "content" in message %}
+            {%- if "<|channel|>analysis<|message|>" in message.content or "<|channel|>final<|message|>" in message.content %}
+                {{- raise_exception("You have passed a message containing <|channel|> tags in the content field. Instead of doing this, you should pass analysis messages (the string between '<|message|>' and '<|end|>') in the 'thinking' field, and final messages (the string between '<|message|>' and '<|end|>') in the 'content' field.") }}
+            {%- endif %}
+        {%- endif %}
+        {%- if "thinking" in message %}
+            {%- if "<|channel|>analysis<|message|>" in message.thinking or "<|channel|>final<|message|>" in message.thinking %}
+                {{- raise_exception("You have passed a message containing <|channel|> tags in the thinking field. Instead of doing this, you should pass analysis messages (the string between '<|message|>' and '<|end|>') in the 'thinking' field, and final messages (the string between '<|message|>' and '<|end|>') in the 'content' field.") }}
+            {%- endif %}
+        {%- endif %}
+        {%- if "tool_calls" in message %}
+            {#- We need very careful handling here - we want to drop the tool call analysis message if the model #}
+            {#- has output a later <|final|> message, but otherwise we want to retain it. This is the only case #}
+            {#- when we render CoT/analysis messages in inference. #}
+            {%- set future_final_message = namespace(found=false) %}
+            {%- for future_message in loop_messages[loop.index:] %}
+                {%- if future_message.role == 'assistant' and "tool_calls" not in future_message %}
+                    {%- set future_final_message.found = true %}
+                {%- endif %}
+            {%- endfor %}
+            {#- We assume max 1 tool call per message, and so we infer the tool call name #}
+            {#- in "tool" messages from the most recent assistant tool call name #}
+            {%- set tool_call = message.tool_calls[0] %}
+            {%- if tool_call.function %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {%- if message.content and message.thinking %}
+                {{- raise_exception("Cannot pass both content and thinking in an assistant message with tool calls! Put the analysis message in one or the other, but not both.") }}
+            {%- elif message.content and not future_final_message.found %}
+                {{- "<|start|>assistant<|channel|>analysis<|message|>" + message.content + "<|end|>" }}
+            {%- elif message.thinking and not future_final_message.found %}
+                {{- "<|start|>assistant<|channel|>analysis<|message|>" + message.thinking + "<|end|>" }}
+            {%- endif %}
+            {{- "<|start|>assistant to=" }}
+            {{- "functions." + tool_call.name + "<|channel|>commentary " }}
+            {{- (tool_call.content_type if tool_call.content_type is defined else "json") + "<|message|>" }}
+            {{- tool_call.arguments|tojson }}
+            {{- "<|call|>" }}
+            {%- set last_tool_call.name = tool_call.name %}
+        {%- elif loop.last and not add_generation_prompt %}
+            {#- Only render the CoT if the final turn is an assistant turn and add_generation_prompt is false #}
+            {#- This is a situation that should only occur in training, never in inference. #}
+            {%- if "thinking" in message %}
+                {{- "<|start|>assistant<|channel|>analysis<|message|>" + message.thinking + "<|end|>" }}
+            {%- endif %}
+            {#- <|return|> indicates the end of generation, but <|end|> does not #}
+            {#- <|return|> should never be an input to the model, but we include it as the final token #}
+            {#- when training, so the model learns to emit it. #}
+            {{- "<|start|>assistant<|channel|>final<|message|>" + message.content + "<|return|>" }}
+        {%- else %}
+            {#- CoT is dropped during all previous turns, so we never render it for inference #}
+            {{- "<|start|>assistant<|channel|>final<|message|>" + message.content + "<|end|>" }}
+            {%- set last_tool_call.name = none %}
+        {%- endif %}
+    {%- elif message.role == 'tool' -%}
+        {%- if last_tool_call.name is none %}
+            {{- raise_exception("Message has tool role, but there was no previous assistant message with a tool call!") }}
+        {%- endif %}
+        {{- "<|start|>functions." + last_tool_call.name }}
+        {{- " to=assistant<|channel|>commentary<|message|>" + message.content|tojson + "<|end|>" }}
+    {%- elif message.role == 'user' -%}
+        {{- "<|start|>user<|message|>" + message.content + "<|end|>" }}
+    {%- endif -%}
+{%- endfor -%}
+
+{#- Generation prompt #}
+{%- if add_generation_prompt -%}
+<|start|>assistant
+{%- endif -%}

citation.json

@@ -0,0 +1,9 @@
+{
+  "title": "GPT-OSS MoE Expert Fingerprinting: Analyzing Expert Activation Patterns in Mixture of Experts Models",
+  "authors": [
+    "Aman Priyanshu",
+    "Supriti Vijay"
+  ],
+  "year": 2025,
+  "url": "https://amanpriyanshu.github.io/GPT-OSS-MoE-ExpertFingerprinting/"
+}

config.json

@@ -0,0 +1,123 @@
+{
+  "vocab_size": 201088,
+  "hidden_size": 2880,
+  "intermediate_size": 2880,
+  "num_hidden_layers": 24,
+  "num_attention_heads": 64,
+  "num_local_experts": 17,
+  "sliding_window": 128,
+  "num_experts_per_tok": 4,
+  "num_key_value_heads": 8,
+  "hidden_act": "silu",
+  "initializer_range": 0.02,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 150000,
+  "rope_scaling": {
+    "beta_fast": 32.0,
+    "beta_slow": 1.0,
+    "factor": 32.0,
+    "original_max_position_embeddings": 4096,
+    "rope_type": "yarn",
+    "truncate": false
+  },
+  "attention_dropout": 0.0,
+  "head_dim": 64,
+  "layer_types": [
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention"
+  ],
+  "attention_bias": true,
+  "max_position_embeddings": 131072,
+  "router_aux_loss_coef": 0.9,
+  "output_router_logits": false,
+  "use_cache": true,
+  "return_dict": true,
+  "output_hidden_states": false,
+  "torchscript": false,
+  "torch_dtype": null,
+  "pruned_heads": {},
+  "tie_word_embeddings": false,
+  "chunk_size_feed_forward": 0,
+  "is_encoder_decoder": false,
+  "is_decoder": false,
+  "cross_attention_hidden_size": null,
+  "add_cross_attention": false,
+  "tie_encoder_decoder": false,
+  "architectures": [
+    "GptOssForCausalLM"
+  ],
+  "finetuning_task": null,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1"
+  },
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1
+  },
+  "task_specific_params": null,
+  "problem_type": null,
+  "tokenizer_class": null,
+  "prefix": null,
+  "bos_token_id": null,
+  "pad_token_id": 199999,
+  "eos_token_id": 200002,
+  "sep_token_id": null,
+  "decoder_start_token_id": null,
+  "max_length": 20,
+  "min_length": 0,
+  "do_sample": false,
+  "early_stopping": false,
+  "num_beams": 1,
+  "num_beam_groups": 1,
+  "diversity_penalty": 0.0,
+  "temperature": 1.0,
+  "top_k": 50,
+  "top_p": 1.0,
+  "typical_p": 1.0,
+  "repetition_penalty": 1.0,
+  "length_penalty": 1.0,
+  "no_repeat_ngram_size": 0,
+  "encoder_no_repeat_ngram_size": 0,
+  "bad_words_ids": null,
+  "num_return_sequences": 1,
+  "output_scores": false,
+  "return_dict_in_generate": false,
+  "forced_bos_token_id": null,
+  "forced_eos_token_id": null,
+  "remove_invalid_values": false,
+  "exponential_decay_length_penalty": null,
+  "suppress_tokens": null,
+  "begin_suppress_tokens": null,
+  "_name_or_path": "openai/gpt-oss-20b",
+  "transformers_version": "4.55.0",
+  "experts_per_token": 4,
+  "initial_context_length": 4096,
+  "model_type": "gpt_oss",
+  "swiglu_limit": 7.0,
+  "tf_legacy_loss": false,
+  "use_bfloat16": false,
+  "output_attentions": false
+}

expert_mapping.json

@@ -0,0 +1,458 @@
+{
+  "0": {
+    "9": 0,
+    "11": 1,
+    "3": 2,
+    "17": 3,
+    "22": 4,
+    "16": 5,
+    "31": 6,
+    "1": 7,
+    "2": 8,
+    "5": 9,
+    "6": 10,
+    "24": 11,
+    "23": 12,
+    "28": 13,
+    "25": 14,
+    "7": 15,
+    "30": 16
+  },
+  "1": {
+    "28": 0,
+    "25": 1,
+    "0": 2,
+    "27": 3,
+    "18": 4,
+    "6": 5,
+    "1": 6,
+    "12": 7,
+    "29": 8,
+    "13": 9,
+    "17": 10,
+    "10": 11,
+    "16": 12,
+    "26": 13,
+    "20": 14,
+    "23": 15,
+    "7": 16
+  },
+  "2": {
+    "31": 0,
+    "21": 1,
+    "29": 2,
+    "10": 3,
+    "8": 4,
+    "5": 5,
+    "0": 6,
+    "22": 7,
+    "28": 8,
+    "20": 9,
+    "27": 10,
+    "3": 11,
+    "6": 12,
+    "16": 13,
+    "15": 14,
+    "4": 15,
+    "7": 16
+  },
+  "3": {
+    "7": 0,
+    "31": 1,
+    "0": 2,
+    "23": 3,
+    "19": 4,
+    "2": 5,
+    "21": 6,
+    "11": 7,
+    "25": 8,
+    "1": 9,
+    "12": 10,
+    "27": 11,
+    "16": 12,
+    "9": 13,
+    "22": 14,
+    "24": 15,
+    "3": 16
+  },
+  "4": {
+    "6": 0,
+    "15": 1,
+    "18": 2,
+    "20": 3,
+    "17": 4,
+    "24": 5,
+    "23": 6,
+    "14": 7,
+    "30": 8,
+    "10": 9,
+    "7": 10,
+    "31": 11,
+    "27": 12,
+    "12": 13,
+    "25": 14,
+    "8": 15,
+    "13": 16
+  },
+  "5": {
+    "6": 0,
+    "0": 1,
+    "10": 2,
+    "31": 3,
+    "14": 4,
+    "15": 5,
+    "2": 6,
+    "24": 7,
+    "17": 8,
+    "18": 9,
+    "27": 10,
+    "8": 11,
+    "30": 12,
+    "21": 13,
+    "26": 14,
+    "4": 15,
+    "22": 16
+  },
+  "6": {
+    "2": 0,
+    "9": 1,
+    "10": 2,
+    "5": 3,
+    "3": 4,
+    "16": 5,
+    "7": 6,
+    "15": 7,
+    "20": 8,
+    "31": 9,
+    "4": 10,
+    "11": 11,
+    "14": 12,
+    "21": 13,
+    "24": 14,
+    "18": 15,
+    "30": 16
+  },
+  "7": {
+    "5": 0,
+    "1": 1,
+    "30": 2,
+    "13": 3,
+    "29": 4,
+    "10": 5,
+    "14": 6,
+    "4": 7,
+    "24": 8,
+    "15": 9,
+    "19": 10,
+    "17": 11,
+    "21": 12,
+    "28": 13,
+    "20": 14,
+    "3": 15,
+    "16": 16
+  },
+  "8": {
+    "24": 0,
+    "20": 1,
+    "4": 2,
+    "17": 3,
+    "31": 4,
+    "5": 5,
+    "0": 6,
+    "13": 7,
+    "23": 8,
+    "30": 9,
+    "19": 10,
+    "9": 11,
+    "6": 12,
+    "26": 13,
+    "8": 14,
+    "10": 15,
+    "28": 16
+  },
+  "9": {
+    "8": 0,
+    "19": 1,
+    "15": 2,
+    "30": 3,
+    "14": 4,
+    "16": 5,
+    "13": 6,
+    "21": 7,
+    "23": 8,
+    "5": 9,
+    "4": 10,
+    "22": 11,
+    "26": 12,
+    "3": 13,
+    "20": 14,
+    "2": 15,
+    "1": 16
+  },
+  "10": {
+    "10": 0,
+    "5": 1,
+    "7": 2,
+    "23": 3,
+    "19": 4,
+    "26": 5,
+    "21": 6,
+    "11": 7,
+    "18": 8,
+    "24": 9,
+    "25": 10,
+    "8": 11,
+    "2": 12,
+    "16": 13,
+    "30": 14,
+    "14": 15,
+    "13": 16
+  },
+  "11": {
+    "30": 0,
+    "9": 1,
+    "27": 2,
+    "11": 3,
+    "7": 4,
+    "20": 5,
+    "25": 6,
+    "21": 7,
+    "4": 8,
+    "17": 9,
+    "15": 10,
+    "23": 11,
+    "18": 12,
+    "12": 13,
+    "24": 14,
+    "13": 15,
+    "26": 16
+  },
+  "12": {
+    "23": 0,
+    "14": 1,
+    "3": 2,
+    "21": 3,
+    "28": 4,
+    "1": 5,
+    "24": 6,
+    "25": 7,
+    "6": 8,
+    "8": 9,
+    "12": 10,
+    "30": 11,
+    "7": 12,
+    "13": 13,
+    "19": 14,
+    "26": 15,
+    "17": 16
+  },
+  "13": {
+    "21": 0,
+    "9": 1,
+    "11": 2,
+    "1": 3,
+    "19": 4,
+    "24": 5,
+    "16": 6,
+    "3": 7,
+    "30": 8,
+    "15": 9,
+    "10": 10,
+    "5": 11,
+    "0": 12,
+    "4": 13,
+    "20": 14,
+    "8": 15,
+    "28": 16
+  },
+  "14": {
+    "9": 0,
+    "0": 1,
+    "6": 2,
+    "18": 3,
+    "21": 4,
+    "26": 5,
+    "4": 6,
+    "24": 7,
+    "1": 8,
+    "31": 9,
+    "3": 10,
+    "29": 11,
+    "11": 12,
+    "12": 13,
+    "27": 14,
+    "13": 15,
+    "17": 16
+  },
+  "15": {
+    "13": 0,
+    "18": 1,
+    "31": 2,
+    "26": 3,
+    "3": 4,
+    "9": 5,
+    "2": 6,
+    "29": 7,
+    "10": 8,
+    "28": 9,
+    "19": 10,
+    "4": 11,
+    "25": 12,
+    "22": 13,
+    "7": 14,
+    "6": 15,
+    "8": 16
+  },
+  "16": {
+    "31": 0,
+    "30": 1,
+    "15": 2,
+    "11": 3,
+    "24": 4,
+    "5": 5,
+    "0": 6,
+    "18": 7,
+    "20": 8,
+    "10": 9,
+    "21": 10,
+    "4": 11,
+    "2": 12,
+    "17": 13,
+    "9": 14,
+    "14": 15,
+    "22": 16
+  },
+  "17": {
+    "14": 0,
+    "30": 1,
+    "5": 2,
+    "4": 3,
+    "17": 4,
+    "11": 5,
+    "28": 6,
+    "7": 7,
+    "25": 8,
+    "8": 9,
+    "12": 10,
+    "13": 11,
+    "2": 12,
+    "19": 13,
+    "24": 14,
+    "0": 15,
+    "22": 16
+  },
+  "18": {
+    "1": 0,
+    "18": 1,
+    "24": 2,
+    "14": 3,
+    "15": 4,
+    "27": 5,
+    "20": 6,
+    "23": 7,
+    "9": 8,
+    "7": 9,
+    "2": 10,
+    "13": 11,
+    "31": 12,
+    "16": 13,
+    "26": 14,
+    "6": 15,
+    "19": 16
+  },
+  "19": {
+    "3": 0,
+    "19": 1,
+    "6": 2,
+    "29": 3,
+    "16": 4,
+    "31": 5,
+    "7": 6,
+    "0": 7,
+    "17": 8,
+    "12": 9,
+    "2": 10,
+    "13": 11,
+    "15": 12,
+    "22": 13,
+    "20": 14,
+    "9": 15,
+    "10": 16
+  },
+  "20": {
+    "22": 0,
+    "16": 1,
+    "30": 2,
+    "24": 3,
+    "31": 4,
+    "21": 5,
+    "11": 6,
+    "12": 7,
+    "0": 8,
+    "13": 9,
+    "7": 10,
+    "25": 11,
+    "23": 12,
+    "10": 13,
+    "6": 14,
+    "5": 15,
+    "4": 16
+  },
+  "21": {
+    "3": 0,
+    "9": 1,
+    "27": 2,
+    "21": 3,
+    "6": 4,
+    "1": 5,
+    "2": 6,
+    "20": 7,
+    "31": 8,
+    "18": 9,
+    "10": 10,
+    "14": 11,
+    "13": 12,
+    "30": 13,
+    "29": 14,
+    "7": 15,
+    "23": 16
+  },
+  "22": {
+    "25": 0,
+    "16": 1,
+    "14": 2,
+    "8": 3,
+    "18": 4,
+    "22": 5,
+    "15": 6,
+    "4": 7,
+    "0": 8,
+    "20": 9,
+    "13": 10,
+    "26": 11,
+    "27": 12,
+    "23": 13,
+    "7": 14,
+    "19": 15,
+    "5": 16
+  },
+  "23": {
+    "31": 0,
+    "18": 1,
+    "10": 2,
+    "16": 3,
+    "0": 4,
+    "22": 5,
+    "28": 6,
+    "17": 7,
+    "8": 8,
+    "3": 9,
+    "14": 10,
+    "19": 11,
+    "25": 12,
+    "27": 13,
+    "13": 14,
+    "24": 15,
+    "23": 16
+  }
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "bos_token_id": 199998,
+  "do_sample": true,
+  "eos_token_id": [
+    200002,
+    199999
+  ],
+  "pad_token_id": 199999,
+  "transformers_version": "4.55.0"
+}

model-00001-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:750157267c7c7237031ac65bc49389d57dad393848348b1a595b752a62e92a5d
+size 1775681762

model-00002-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:679922bb06d4cfdb6590025c40978c41baad1b1f5707f6b669b75fb22d2562cd
+size 1799068508

model-00003-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:385c273764c838e1c0fa540a90086278ef2832ebf5d77c03adfb55edc2274bc3
+size 1799068508

model-00004-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d36b7cd3c284dd8607bd7026095593d8c47fa22591e73543d26ef59faea1916
+size 1799068508

model-00005-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2aa6de9729b7cda532b9bd03579579b86804e8c3a37a10fdd420bf06bd10e595
+size 1799068508

model-00006-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4cddd20f5246bc7d6d47b0a4e0943ccf96028c1d6c39422320baeb091b34fe1
+size 1799068508

model-00007-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40f16cd7be6f03e7d9dcce322447af014374d3e790b9e457542f570c0cfc0ac3
+size 1799068540

model-00008-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01176718b07b495bf6a6e93c728918aebf1eae74a7f60950d1faf1e6e1227b8b
+size 1799068540

model-00009-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f67bb027b5f97da55ec51b6c60d6645df321ea5178bd22e90730f3ac93d79a9d
+size 1799068540

model-00010-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ad80b1354de490358df71cc5d71cecc7a3c5a8c0ffc181536da6963987d1240
+size 1799068540

model-00011-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a22dd4e4c107a8331b941967408ab3e2820e0fdc9b10fd44de223df92f233fde
+size 1799068540

model-00012-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:947dca0405f43c960aaff6b29b7c611475dbfe2a2ef39d302905aad2bba466f3
+size 1799068540

model-00013-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:944fd063bf3e1eb0abd900c1f3d6124809b5a8a47f57a81e3abdb27e24997298
+size 1181659634

model-00014-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08e257de1fa16cf80c8a36ca29c5974fc999f0dc7ada1468bfd0be18151af482
+size 1158267008

model.safetensors.index.json

@@ -0,0 +1,419 @@
+{
+  "metadata": {
+    "total_parameters": 11952657624,
+    "total_size": 23905315248
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00014-of-00014.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.0.mlp.experts.down_proj": "model-00002-of-00014.safetensors",
+    "model.layers.0.mlp.experts.down_proj_bias": "model-00002-of-00014.safetensors",
+    "model.layers.0.mlp.experts.gate_up_proj": "model-00001-of-00014.safetensors",
+    "model.layers.0.mlp.experts.gate_up_proj_bias": "model-00001-of-00014.safetensors",
+    "model.layers.0.mlp.router.bias": "model-00001-of-00014.safetensors",
+    "model.layers.0.mlp.router.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.o_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.sinks": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.1.mlp.experts.down_proj": "model-00002-of-00014.safetensors",
+    "model.layers.1.mlp.experts.down_proj_bias": "model-00002-of-00014.safetensors",
+    "model.layers.1.mlp.experts.gate_up_proj": "model-00002-of-00014.safetensors",
+    "model.layers.1.mlp.experts.gate_up_proj_bias": "model-00002-of-00014.safetensors",
+    "model.layers.1.mlp.router.bias": "model-00002-of-00014.safetensors",
+    "model.layers.1.mlp.router.weight": "model-00002-of-00014.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.1.self_attn.o_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.1.self_attn.sinks": "model-00002-of-00014.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.10.mlp.experts.down_proj": "model-00007-of-00014.safetensors",
+    "model.layers.10.mlp.experts.down_proj_bias": "model-00007-of-00014.safetensors",
+    "model.layers.10.mlp.experts.gate_up_proj": "model-00006-of-00014.safetensors",
+    "model.layers.10.mlp.experts.gate_up_proj_bias": "model-00006-of-00014.safetensors",
+    "model.layers.10.mlp.router.bias": "model-00006-of-00014.safetensors",
+    "model.layers.10.mlp.router.weight": "model-00006-of-00014.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.10.self_attn.o_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.10.self_attn.sinks": "model-00006-of-00014.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.11.mlp.experts.down_proj": "model-00007-of-00014.safetensors",
+    "model.layers.11.mlp.experts.down_proj_bias": "model-00007-of-00014.safetensors",
+    "model.layers.11.mlp.experts.gate_up_proj": "model-00007-of-00014.safetensors",
+    "model.layers.11.mlp.experts.gate_up_proj_bias": "model-00007-of-00014.safetensors",
+    "model.layers.11.mlp.router.bias": "model-00007-of-00014.safetensors",
+    "model.layers.11.mlp.router.weight": "model-00007-of-00014.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.11.self_attn.o_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.11.self_attn.sinks": "model-00007-of-00014.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.12.mlp.experts.down_proj": "model-00008-of-00014.safetensors",
+    "model.layers.12.mlp.experts.down_proj_bias": "model-00008-of-00014.safetensors",
+    "model.layers.12.mlp.experts.gate_up_proj": "model-00007-of-00014.safetensors",
+    "model.layers.12.mlp.experts.gate_up_proj_bias": "model-00007-of-00014.safetensors",
+    "model.layers.12.mlp.router.bias": "model-00007-of-00014.safetensors",
+    "model.layers.12.mlp.router.weight": "model-00007-of-00014.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.12.self_attn.o_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.12.self_attn.sinks": "model-00007-of-00014.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.13.mlp.experts.down_proj": "model-00008-of-00014.safetensors",
+    "model.layers.13.mlp.experts.down_proj_bias": "model-00008-of-00014.safetensors",
+    "model.layers.13.mlp.experts.gate_up_proj": "model-00008-of-00014.safetensors",
+    "model.layers.13.mlp.experts.gate_up_proj_bias": "model-00008-of-00014.safetensors",
+    "model.layers.13.mlp.router.bias": "model-00008-of-00014.safetensors",
+    "model.layers.13.mlp.router.weight": "model-00008-of-00014.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.13.self_attn.o_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.13.self_attn.sinks": "model-00008-of-00014.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.14.mlp.experts.down_proj": "model-00009-of-00014.safetensors",
+    "model.layers.14.mlp.experts.down_proj_bias": "model-00009-of-00014.safetensors",
+    "model.layers.14.mlp.experts.gate_up_proj": "model-00008-of-00014.safetensors",
+    "model.layers.14.mlp.experts.gate_up_proj_bias": "model-00008-of-00014.safetensors",
+    "model.layers.14.mlp.router.bias": "model-00008-of-00014.safetensors",
+    "model.layers.14.mlp.router.weight": "model-00008-of-00014.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.14.self_attn.o_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.14.self_attn.sinks": "model-00008-of-00014.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.15.mlp.experts.down_proj": "model-00009-of-00014.safetensors",
+    "model.layers.15.mlp.experts.down_proj_bias": "model-00009-of-00014.safetensors",
+    "model.layers.15.mlp.experts.gate_up_proj": "model-00009-of-00014.safetensors",
+    "model.layers.15.mlp.experts.gate_up_proj_bias": "model-00009-of-00014.safetensors",
+    "model.layers.15.mlp.router.bias": "model-00009-of-00014.safetensors",
+    "model.layers.15.mlp.router.weight": "model-00009-of-00014.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.15.self_attn.o_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.15.self_attn.sinks": "model-00009-of-00014.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.16.mlp.experts.down_proj": "model-00010-of-00014.safetensors",
+    "model.layers.16.mlp.experts.down_proj_bias": "model-00010-of-00014.safetensors",
+    "model.layers.16.mlp.experts.gate_up_proj": "model-00009-of-00014.safetensors",
+    "model.layers.16.mlp.experts.gate_up_proj_bias": "model-00009-of-00014.safetensors",
+    "model.layers.16.mlp.router.bias": "model-00009-of-00014.safetensors",
+    "model.layers.16.mlp.router.weight": "model-00009-of-00014.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.16.self_attn.o_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.16.self_attn.sinks": "model-00009-of-00014.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.17.mlp.experts.down_proj": "model-00010-of-00014.safetensors",
+    "model.layers.17.mlp.experts.down_proj_bias": "model-00010-of-00014.safetensors",
+    "model.layers.17.mlp.experts.gate_up_proj": "model-00010-of-00014.safetensors",
+    "model.layers.17.mlp.experts.gate_up_proj_bias": "model-00010-of-00014.safetensors",
+    "model.layers.17.mlp.router.bias": "model-00010-of-00014.safetensors",
+    "model.layers.17.mlp.router.weight": "model-00010-of-00014.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.17.self_attn.o_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.17.self_attn.sinks": "model-00010-of-00014.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.18.mlp.experts.down_proj": "model-00011-of-00014.safetensors",
+    "model.layers.18.mlp.experts.down_proj_bias": "model-00011-of-00014.safetensors",
+    "model.layers.18.mlp.experts.gate_up_proj": "model-00010-of-00014.safetensors",
+    "model.layers.18.mlp.experts.gate_up_proj_bias": "model-00010-of-00014.safetensors",
+    "model.layers.18.mlp.router.bias": "model-00010-of-00014.safetensors",
+    "model.layers.18.mlp.router.weight": "model-00010-of-00014.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.18.self_attn.o_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.18.self_attn.sinks": "model-00010-of-00014.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.19.mlp.experts.down_proj": "model-00011-of-00014.safetensors",
+    "model.layers.19.mlp.experts.down_proj_bias": "model-00011-of-00014.safetensors",
+    "model.layers.19.mlp.experts.gate_up_proj": "model-00011-of-00014.safetensors",
+    "model.layers.19.mlp.experts.gate_up_proj_bias": "model-00011-of-00014.safetensors",
+    "model.layers.19.mlp.router.bias": "model-00011-of-00014.safetensors",
+    "model.layers.19.mlp.router.weight": "model-00011-of-00014.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.19.self_attn.o_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.19.self_attn.sinks": "model-00011-of-00014.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.2.mlp.experts.down_proj": "model-00003-of-00014.safetensors",
+    "model.layers.2.mlp.experts.down_proj_bias": "model-00003-of-00014.safetensors",
+    "model.layers.2.mlp.experts.gate_up_proj": "model-00002-of-00014.safetensors",
+    "model.layers.2.mlp.experts.gate_up_proj_bias": "model-00002-of-00014.safetensors",
+    "model.layers.2.mlp.router.bias": "model-00002-of-00014.safetensors",
+    "model.layers.2.mlp.router.weight": "model-00002-of-00014.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.2.self_attn.o_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.2.self_attn.sinks": "model-00002-of-00014.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.20.mlp.experts.down_proj": "model-00012-of-00014.safetensors",
+    "model.layers.20.mlp.experts.down_proj_bias": "model-00012-of-00014.safetensors",
+    "model.layers.20.mlp.experts.gate_up_proj": "model-00011-of-00014.safetensors",
+    "model.layers.20.mlp.experts.gate_up_proj_bias": "model-00011-of-00014.safetensors",
+    "model.layers.20.mlp.router.bias": "model-00011-of-00014.safetensors",
+    "model.layers.20.mlp.router.weight": "model-00011-of-00014.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.20.self_attn.o_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.20.self_attn.sinks": "model-00011-of-00014.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.21.mlp.experts.down_proj": "model-00012-of-00014.safetensors",
+    "model.layers.21.mlp.experts.down_proj_bias": "model-00012-of-00014.safetensors",
+    "model.layers.21.mlp.experts.gate_up_proj": "model-00012-of-00014.safetensors",
+    "model.layers.21.mlp.experts.gate_up_proj_bias": "model-00012-of-00014.safetensors",
+    "model.layers.21.mlp.router.bias": "model-00012-of-00014.safetensors",
+    "model.layers.21.mlp.router.weight": "model-00012-of-00014.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.21.self_attn.o_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.21.self_attn.sinks": "model-00012-of-00014.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.22.mlp.experts.down_proj": "model-00013-of-00014.safetensors",
+    "model.layers.22.mlp.experts.down_proj_bias": "model-00013-of-00014.safetensors",
+    "model.layers.22.mlp.experts.gate_up_proj": "model-00012-of-00014.safetensors",
+    "model.layers.22.mlp.experts.gate_up_proj_bias": "model-00012-of-00014.safetensors",
+    "model.layers.22.mlp.router.bias": "model-00012-of-00014.safetensors",
+    "model.layers.22.mlp.router.weight": "model-00012-of-00014.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.22.self_attn.o_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.22.self_attn.sinks": "model-00012-of-00014.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.23.mlp.experts.down_proj": "model-00013-of-00014.safetensors",
+    "model.layers.23.mlp.experts.down_proj_bias": "model-00013-of-00014.safetensors",
+    "model.layers.23.mlp.experts.gate_up_proj": "model-00013-of-00014.safetensors",
+    "model.layers.23.mlp.experts.gate_up_proj_bias": "model-00013-of-00014.safetensors",
+    "model.layers.23.mlp.router.bias": "model-00013-of-00014.safetensors",
+    "model.layers.23.mlp.router.weight": "model-00013-of-00014.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.23.self_attn.o_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.23.self_attn.sinks": "model-00013-of-00014.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.3.mlp.experts.down_proj": "model-00003-of-00014.safetensors",
+    "model.layers.3.mlp.experts.down_proj_bias": "model-00003-of-00014.safetensors",
+    "model.layers.3.mlp.experts.gate_up_proj": "model-00003-of-00014.safetensors",
+    "model.layers.3.mlp.experts.gate_up_proj_bias": "model-00003-of-00014.safetensors",
+    "model.layers.3.mlp.router.bias": "model-00003-of-00014.safetensors",
+    "model.layers.3.mlp.router.weight": "model-00003-of-00014.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.3.self_attn.o_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.3.self_attn.sinks": "model-00003-of-00014.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.4.mlp.experts.down_proj": "model-00004-of-00014.safetensors",
+    "model.layers.4.mlp.experts.down_proj_bias": "model-00004-of-00014.safetensors",
+    "model.layers.4.mlp.experts.gate_up_proj": "model-00003-of-00014.safetensors",
+    "model.layers.4.mlp.experts.gate_up_proj_bias": "model-00003-of-00014.safetensors",
+    "model.layers.4.mlp.router.bias": "model-00003-of-00014.safetensors",
+    "model.layers.4.mlp.router.weight": "model-00003-of-00014.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.4.self_attn.o_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.4.self_attn.sinks": "model-00003-of-00014.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.5.mlp.experts.down_proj": "model-00004-of-00014.safetensors",
+    "model.layers.5.mlp.experts.down_proj_bias": "model-00004-of-00014.safetensors",
+    "model.layers.5.mlp.experts.gate_up_proj": "model-00004-of-00014.safetensors",
+    "model.layers.5.mlp.experts.gate_up_proj_bias": "model-00004-of-00014.safetensors",
+    "model.layers.5.mlp.router.bias": "model-00004-of-00014.safetensors",
+    "model.layers.5.mlp.router.weight": "model-00004-of-00014.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.5.self_attn.o_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.5.self_attn.sinks": "model-00004-of-00014.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.6.mlp.experts.down_proj": "model-00005-of-00014.safetensors",
+    "model.layers.6.mlp.experts.down_proj_bias": "model-00005-of-00014.safetensors",
+    "model.layers.6.mlp.experts.gate_up_proj": "model-00004-of-00014.safetensors",
+    "model.layers.6.mlp.experts.gate_up_proj_bias": "model-00004-of-00014.safetensors",
+    "model.layers.6.mlp.router.bias": "model-00004-of-00014.safetensors",
+    "model.layers.6.mlp.router.weight": "model-00004-of-00014.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.6.self_attn.o_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.6.self_attn.sinks": "model-00004-of-00014.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.7.mlp.experts.down_proj": "model-00005-of-00014.safetensors",
+    "model.layers.7.mlp.experts.down_proj_bias": "model-00005-of-00014.safetensors",
+    "model.layers.7.mlp.experts.gate_up_proj": "model-00005-of-00014.safetensors",
+    "model.layers.7.mlp.experts.gate_up_proj_bias": "model-00005-of-00014.safetensors",
+    "model.layers.7.mlp.router.bias": "model-00005-of-00014.safetensors",
+    "model.layers.7.mlp.router.weight": "model-00005-of-00014.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.7.self_attn.o_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.7.self_attn.sinks": "model-00005-of-00014.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.8.mlp.experts.down_proj": "model-00006-of-00014.safetensors",
+    "model.layers.8.mlp.experts.down_proj_bias": "model-00006-of-00014.safetensors",
+    "model.layers.8.mlp.experts.gate_up_proj": "model-00005-of-00014.safetensors",
+    "model.layers.8.mlp.experts.gate_up_proj_bias": "model-00005-of-00014.safetensors",
+    "model.layers.8.mlp.router.bias": "model-00005-of-00014.safetensors",
+    "model.layers.8.mlp.router.weight": "model-00005-of-00014.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.8.self_attn.o_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.8.self_attn.sinks": "model-00005-of-00014.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.9.mlp.experts.down_proj": "model-00006-of-00014.safetensors",
+    "model.layers.9.mlp.experts.down_proj_bias": "model-00006-of-00014.safetensors",
+    "model.layers.9.mlp.experts.gate_up_proj": "model-00006-of-00014.safetensors",
+    "model.layers.9.mlp.experts.gate_up_proj_bias": "model-00006-of-00014.safetensors",
+    "model.layers.9.mlp.router.bias": "model-00006-of-00014.safetensors",
+    "model.layers.9.mlp.router.weight": "model-00006-of-00014.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.9.self_attn.o_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.9.self_attn.sinks": "model-00006-of-00014.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.norm.weight": "model-00013-of-00014.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|return|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0614fe83cadab421296e664e1f48f4261fa8fef6e03e63bb75c20f38e37d07d3
+size 27868174

tokenizer_config.json

@@ -0,0 +1,183 @@
+{
+  "added_tokens_decoder": {
+    "199998": {
+      "content": "<|startoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "199999": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200000": {
+      "content": "<|reserved_200000|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200001": {
+      "content": "<|reserved_200001|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200002": {
+      "content": "<|return|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200003": {
+      "content": "<|constrain|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200004": {
+      "content": "<|reserved_200004|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200005": {
+      "content": "<|channel|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200006": {
+      "content": "<|start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200007": {
+      "content": "<|end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200008": {
+      "content": "<|message|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200009": {
+      "content": "<|reserved_200009|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200010": {
+      "content": "<|reserved_200010|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200011": {
+      "content": "<|reserved_200011|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200012": {
+      "content": "<|call|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200013": {
+      "content": "<|reserved_200013|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200014": {
+      "content": "<|reserved_200014|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200015": {
+      "content": "<|reserved_200015|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200016": {
+      "content": "<|reserved_200016|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200017": {
+      "content": "<|reserved_200017|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200018": {
+      "content": "<|endofprompt|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|return|>",
+  "extra_special_tokens": {},
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}