ysn-rfd commited on
Commit
6b9a528
Β·
verified Β·
1 Parent(s): 0a50ee9

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +95 -0
README.md ADDED
@@ -0,0 +1,95 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: MaziyarPanahi/calme-3.3-llamaloi-3b
3
+ datasets:
4
+ - MaziyarPanahi/calme-legalkit-v0.2
5
+ language:
6
+ - fr
7
+ - en
8
+ library_name: transformers
9
+ license: llama3.2
10
+ model_name: calme-3.3-llamaloi-3b
11
+ pipeline_tag: text-generation
12
+ tags:
13
+ - chat
14
+ - llama
15
+ - llama3
16
+ - finetune
17
+ - french
18
+ - legal
19
+ - loi
20
+ - llama-cpp
21
+ - matrixportal
22
+ inference: false
23
+ model_creator: MaziyarPanahi
24
+ quantized_by: MaziyarPanahi
25
+ ---
26
+
27
+ # ysn-rfd/calme-3.3-llamaloi-3b-GGUF
28
+ This model was converted to GGUF format from [`MaziyarPanahi/calme-3.3-llamaloi-3b`](https://huggingface.co/MaziyarPanahi/calme-3.3-llamaloi-3b) using llama.cpp via the ggml.ai's [all-gguf-same-where](https://huggingface.co/spaces/matrixportal/all-gguf-same-where) space.
29
+ Refer to the [original model card](https://huggingface.co/MaziyarPanahi/calme-3.3-llamaloi-3b) for more details on the model.
30
+
31
+ ## βœ… Quantized Models Download List
32
+
33
+ ### πŸ” Recommended Quantizations
34
+ - **✨ General CPU Use:** [`Q4_K_M`](https://huggingface.co/ysn-rfd/calme-3.3-llamaloi-3b-GGUF/resolve/main/calme-3.3-llamaloi-3b-q4_k_m.gguf) (Best balance of speed/quality)
35
+ - **πŸ“± ARM Devices:** [`Q4_0`](https://huggingface.co/ysn-rfd/calme-3.3-llamaloi-3b-GGUF/resolve/main/calme-3.3-llamaloi-3b-q4_0.gguf) (Optimized for ARM CPUs)
36
+ - **πŸ† Maximum Quality:** [`Q8_0`](https://huggingface.co/ysn-rfd/calme-3.3-llamaloi-3b-GGUF/resolve/main/calme-3.3-llamaloi-3b-q8_0.gguf) (Near-original quality)
37
+
38
+ ### πŸ“¦ Full Quantization Options
39
+ | πŸš€ Download | πŸ”’ Type | πŸ“ Notes |
40
+ |:---------|:-----|:------|
41
+ | [Download](https://huggingface.co/ysn-rfd/calme-3.3-llamaloi-3b-GGUF/resolve/main/calme-3.3-llamaloi-3b-q2_k.gguf) | ![Q2_K](https://img.shields.io/badge/Q2_K-1A73E8) | Basic quantization |
42
+ | [Download](https://huggingface.co/ysn-rfd/calme-3.3-llamaloi-3b-GGUF/resolve/main/calme-3.3-llamaloi-3b-q3_k_s.gguf) | ![Q3_K_S](https://img.shields.io/badge/Q3_K_S-34A853) | Small size |
43
+ | [Download](https://huggingface.co/ysn-rfd/calme-3.3-llamaloi-3b-GGUF/resolve/main/calme-3.3-llamaloi-3b-q3_k_m.gguf) | ![Q3_K_M](https://img.shields.io/badge/Q3_K_M-FBBC05) | Balanced quality |
44
+ | [Download](https://huggingface.co/ysn-rfd/calme-3.3-llamaloi-3b-GGUF/resolve/main/calme-3.3-llamaloi-3b-q3_k_l.gguf) | ![Q3_K_L](https://img.shields.io/badge/Q3_K_L-4285F4) | Better quality |
45
+ | [Download](https://huggingface.co/ysn-rfd/calme-3.3-llamaloi-3b-GGUF/resolve/main/calme-3.3-llamaloi-3b-q4_0.gguf) | ![Q4_0](https://img.shields.io/badge/Q4_0-EA4335) | Fast on ARM |
46
+ | [Download](https://huggingface.co/ysn-rfd/calme-3.3-llamaloi-3b-GGUF/resolve/main/calme-3.3-llamaloi-3b-q4_k_s.gguf) | ![Q4_K_S](https://img.shields.io/badge/Q4_K_S-673AB7) | Fast, recommended |
47
+ | [Download](https://huggingface.co/ysn-rfd/calme-3.3-llamaloi-3b-GGUF/resolve/main/calme-3.3-llamaloi-3b-q4_k_m.gguf) | ![Q4_K_M](https://img.shields.io/badge/Q4_K_M-673AB7) ⭐ | Best balance |
48
+ | [Download](https://huggingface.co/ysn-rfd/calme-3.3-llamaloi-3b-GGUF/resolve/main/calme-3.3-llamaloi-3b-q5_0.gguf) | ![Q5_0](https://img.shields.io/badge/Q5_0-FF6D01) | Good quality |
49
+ | [Download](https://huggingface.co/ysn-rfd/calme-3.3-llamaloi-3b-GGUF/resolve/main/calme-3.3-llamaloi-3b-q5_k_s.gguf) | ![Q5_K_S](https://img.shields.io/badge/Q5_K_S-0F9D58) | Balanced |
50
+ | [Download](https://huggingface.co/ysn-rfd/calme-3.3-llamaloi-3b-GGUF/resolve/main/calme-3.3-llamaloi-3b-q5_k_m.gguf) | ![Q5_K_M](https://img.shields.io/badge/Q5_K_M-0F9D58) | High quality |
51
+ | [Download](https://huggingface.co/ysn-rfd/calme-3.3-llamaloi-3b-GGUF/resolve/main/calme-3.3-llamaloi-3b-q6_k.gguf) | ![Q6_K](https://img.shields.io/badge/Q6_K-4285F4) πŸ† | Very good quality |
52
+ | [Download](https://huggingface.co/ysn-rfd/calme-3.3-llamaloi-3b-GGUF/resolve/main/calme-3.3-llamaloi-3b-q8_0.gguf) | ![Q8_0](https://img.shields.io/badge/Q8_0-EA4335) ⚑ | Fast, best quality |
53
+ | [Download](https://huggingface.co/ysn-rfd/calme-3.3-llamaloi-3b-GGUF/resolve/main/calme-3.3-llamaloi-3b-f16.gguf) | ![F16](https://img.shields.io/badge/F16-000000) | Maximum accuracy |
54
+
55
+ πŸ’‘ **Tip:** Use `F16` for maximum precision when quality is critical
56
+
57
+
58
+ ---
59
+ # πŸš€ Applications and Tools for Locally Quantized LLMs
60
+ ## πŸ–₯️ Desktop Applications
61
+
62
+ | Application | Description | Download Link |
63
+ |-----------------|----------------------------------------------------------------------------------------------|--------------------------------------------------------------------------------|
64
+ | **Llama.cpp** | A fast and efficient inference engine for GGUF models. | [GitHub Repository](https://github.com/ggml-org/llama.cpp) |
65
+ | **Ollama** | A streamlined solution for running LLMs locally. | [Website](https://ollama.com/) |
66
+ | **AnythingLLM** | An AI-powered knowledge management tool. | [GitHub Repository](https://github.com/Mintplex-Labs/anything-llm) |
67
+ | **Open WebUI** | A user-friendly web interface for running local LLMs. | [GitHub Repository](https://github.com/open-webui/open-webui) |
68
+ | **GPT4All** | A user-friendly desktop application supporting various LLMs, compatible with GGUF models. | [GitHub Repository](https://github.com/nomic-ai/gpt4all) |
69
+ | **LM Studio** | A desktop application designed to run and manage local LLMs, supporting GGUF format. | [Website](https://lmstudio.ai/) |
70
+ | **GPT4All Chat**| A chat application compatible with GGUF models for local, offline interactions. | [GitHub Repository](https://github.com/nomic-ai/gpt4all) |
71
+
72
+ ---
73
+
74
+ ## πŸ“± Mobile Applications
75
+
76
+ | Application | Description | Download Link |
77
+ |-------------------|----------------------------------------------------------------------------------------------|--------------------------------------------------------------------------------|
78
+ | **ChatterUI** | A simple and lightweight LLM app for mobile devices. | [GitHub Repository](https://github.com/Vali-98/ChatterUI) |
79
+ | **Maid** | Mobile Artificial Intelligence Distribution for running AI models on mobile devices. | [GitHub Repository](https://github.com/Mobile-Artificial-Intelligence/maid) |
80
+ | **PocketPal AI** | A mobile AI assistant powered by local models. | [GitHub Repository](https://github.com/a-ghorbani/pocketpal-ai) |
81
+ | **Layla** | A flexible platform for running various AI models on mobile devices. | [Website](https://www.layla-network.ai/) |
82
+
83
+ ---
84
+
85
+ ## 🎨 Image Generation Applications
86
+
87
+ | Application | Description | Download Link |
88
+ |-------------------------------------|----------------------------------------------------------------------------------------------|--------------------------------------------------------------------------------|
89
+ | **Stable Diffusion** | An open-source AI model for generating images from text. | [GitHub Repository](https://github.com/CompVis/stable-diffusion) |
90
+ | **Stable Diffusion WebUI** | A web application providing access to Stable Diffusion models via a browser interface. | [GitHub Repository](https://github.com/AUTOMATIC1111/stable-diffusion-webui) |
91
+ | **Local Dream** | Android Stable Diffusion with Snapdragon NPU acceleration. Also supports CPU inference. | [GitHub Repository](https://github.com/xororz/local-dream) |
92
+ | **Stable-Diffusion-Android (SDAI)** | An open-source AI art application for Android devices, enabling digital art creation. | [GitHub Repository](https://github.com/ShiftHackZ/Stable-Diffusion-Android) |
93
+
94
+ ---
95
+