Upload README.md with huggingface_hub
Browse files
README.md
ADDED
|
@@ -0,0 +1,290 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: Locutusque/TinyMistral-248M-v2.5
|
| 3 |
+
datasets:
|
| 4 |
+
- open-phi/programming_books_llama
|
| 5 |
+
- open-phi/textbooks
|
| 6 |
+
language:
|
| 7 |
+
- en
|
| 8 |
+
- code
|
| 9 |
+
license: apache-2.0
|
| 10 |
+
tags:
|
| 11 |
+
- merge
|
| 12 |
+
- computer science
|
| 13 |
+
- llama-cpp
|
| 14 |
+
- matrixportal
|
| 15 |
+
inference:
|
| 16 |
+
parameters:
|
| 17 |
+
do_sample: true
|
| 18 |
+
temperature: 0.2
|
| 19 |
+
top_p: 0.14
|
| 20 |
+
top_k: 12
|
| 21 |
+
max_new_tokens: 250
|
| 22 |
+
repetition_penalty: 1.15
|
| 23 |
+
widget:
|
| 24 |
+
- text: 'To calculate the factorial of n, we can use the following function:'
|
| 25 |
+
model-index:
|
| 26 |
+
- name: TinyMistral-248M-v2.5
|
| 27 |
+
results:
|
| 28 |
+
- task:
|
| 29 |
+
type: text-generation
|
| 30 |
+
name: Text Generation
|
| 31 |
+
dataset:
|
| 32 |
+
name: AI2 Reasoning Challenge (25-Shot)
|
| 33 |
+
type: ai2_arc
|
| 34 |
+
config: ARC-Challenge
|
| 35 |
+
split: test
|
| 36 |
+
args:
|
| 37 |
+
num_few_shot: 25
|
| 38 |
+
metrics:
|
| 39 |
+
- type: acc_norm
|
| 40 |
+
value: 24.57
|
| 41 |
+
name: normalized accuracy
|
| 42 |
+
source:
|
| 43 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/TinyMistral-248M-v2.5
|
| 44 |
+
name: Open LLM Leaderboard
|
| 45 |
+
- task:
|
| 46 |
+
type: text-generation
|
| 47 |
+
name: Text Generation
|
| 48 |
+
dataset:
|
| 49 |
+
name: HellaSwag (10-Shot)
|
| 50 |
+
type: hellaswag
|
| 51 |
+
split: validation
|
| 52 |
+
args:
|
| 53 |
+
num_few_shot: 10
|
| 54 |
+
metrics:
|
| 55 |
+
- type: acc_norm
|
| 56 |
+
value: 27.49
|
| 57 |
+
name: normalized accuracy
|
| 58 |
+
source:
|
| 59 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/TinyMistral-248M-v2.5
|
| 60 |
+
name: Open LLM Leaderboard
|
| 61 |
+
- task:
|
| 62 |
+
type: text-generation
|
| 63 |
+
name: Text Generation
|
| 64 |
+
dataset:
|
| 65 |
+
name: MMLU (5-Shot)
|
| 66 |
+
type: cais/mmlu
|
| 67 |
+
config: all
|
| 68 |
+
split: test
|
| 69 |
+
args:
|
| 70 |
+
num_few_shot: 5
|
| 71 |
+
metrics:
|
| 72 |
+
- type: acc
|
| 73 |
+
value: 23.15
|
| 74 |
+
name: accuracy
|
| 75 |
+
source:
|
| 76 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/TinyMistral-248M-v2.5
|
| 77 |
+
name: Open LLM Leaderboard
|
| 78 |
+
- task:
|
| 79 |
+
type: text-generation
|
| 80 |
+
name: Text Generation
|
| 81 |
+
dataset:
|
| 82 |
+
name: TruthfulQA (0-shot)
|
| 83 |
+
type: truthful_qa
|
| 84 |
+
config: multiple_choice
|
| 85 |
+
split: validation
|
| 86 |
+
args:
|
| 87 |
+
num_few_shot: 0
|
| 88 |
+
metrics:
|
| 89 |
+
- type: mc2
|
| 90 |
+
value: 46.72
|
| 91 |
+
source:
|
| 92 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/TinyMistral-248M-v2.5
|
| 93 |
+
name: Open LLM Leaderboard
|
| 94 |
+
- task:
|
| 95 |
+
type: text-generation
|
| 96 |
+
name: Text Generation
|
| 97 |
+
dataset:
|
| 98 |
+
name: Winogrande (5-shot)
|
| 99 |
+
type: winogrande
|
| 100 |
+
config: winogrande_xl
|
| 101 |
+
split: validation
|
| 102 |
+
args:
|
| 103 |
+
num_few_shot: 5
|
| 104 |
+
metrics:
|
| 105 |
+
- type: acc
|
| 106 |
+
value: 47.83
|
| 107 |
+
name: accuracy
|
| 108 |
+
source:
|
| 109 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/TinyMistral-248M-v2.5
|
| 110 |
+
name: Open LLM Leaderboard
|
| 111 |
+
- task:
|
| 112 |
+
type: text-generation
|
| 113 |
+
name: Text Generation
|
| 114 |
+
dataset:
|
| 115 |
+
name: GSM8k (5-shot)
|
| 116 |
+
type: gsm8k
|
| 117 |
+
config: main
|
| 118 |
+
split: test
|
| 119 |
+
args:
|
| 120 |
+
num_few_shot: 5
|
| 121 |
+
metrics:
|
| 122 |
+
- type: acc
|
| 123 |
+
value: 0.0
|
| 124 |
+
name: accuracy
|
| 125 |
+
source:
|
| 126 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/TinyMistral-248M-v2.5
|
| 127 |
+
name: Open LLM Leaderboard
|
| 128 |
+
- task:
|
| 129 |
+
type: text-generation
|
| 130 |
+
name: Text Generation
|
| 131 |
+
dataset:
|
| 132 |
+
name: IFEval (0-Shot)
|
| 133 |
+
type: HuggingFaceH4/ifeval
|
| 134 |
+
args:
|
| 135 |
+
num_few_shot: 0
|
| 136 |
+
metrics:
|
| 137 |
+
- type: inst_level_strict_acc and prompt_level_strict_acc
|
| 138 |
+
value: 13.36
|
| 139 |
+
name: strict accuracy
|
| 140 |
+
source:
|
| 141 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Locutusque/TinyMistral-248M-v2.5
|
| 142 |
+
name: Open LLM Leaderboard
|
| 143 |
+
- task:
|
| 144 |
+
type: text-generation
|
| 145 |
+
name: Text Generation
|
| 146 |
+
dataset:
|
| 147 |
+
name: BBH (3-Shot)
|
| 148 |
+
type: BBH
|
| 149 |
+
args:
|
| 150 |
+
num_few_shot: 3
|
| 151 |
+
metrics:
|
| 152 |
+
- type: acc_norm
|
| 153 |
+
value: 3.18
|
| 154 |
+
name: normalized accuracy
|
| 155 |
+
source:
|
| 156 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Locutusque/TinyMistral-248M-v2.5
|
| 157 |
+
name: Open LLM Leaderboard
|
| 158 |
+
- task:
|
| 159 |
+
type: text-generation
|
| 160 |
+
name: Text Generation
|
| 161 |
+
dataset:
|
| 162 |
+
name: MATH Lvl 5 (4-Shot)
|
| 163 |
+
type: hendrycks/competition_math
|
| 164 |
+
args:
|
| 165 |
+
num_few_shot: 4
|
| 166 |
+
metrics:
|
| 167 |
+
- type: exact_match
|
| 168 |
+
value: 0.0
|
| 169 |
+
name: exact match
|
| 170 |
+
source:
|
| 171 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Locutusque/TinyMistral-248M-v2.5
|
| 172 |
+
name: Open LLM Leaderboard
|
| 173 |
+
- task:
|
| 174 |
+
type: text-generation
|
| 175 |
+
name: Text Generation
|
| 176 |
+
dataset:
|
| 177 |
+
name: GPQA (0-shot)
|
| 178 |
+
type: Idavidrein/gpqa
|
| 179 |
+
args:
|
| 180 |
+
num_few_shot: 0
|
| 181 |
+
metrics:
|
| 182 |
+
- type: acc_norm
|
| 183 |
+
value: 0.11
|
| 184 |
+
name: acc_norm
|
| 185 |
+
source:
|
| 186 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Locutusque/TinyMistral-248M-v2.5
|
| 187 |
+
name: Open LLM Leaderboard
|
| 188 |
+
- task:
|
| 189 |
+
type: text-generation
|
| 190 |
+
name: Text Generation
|
| 191 |
+
dataset:
|
| 192 |
+
name: MuSR (0-shot)
|
| 193 |
+
type: TAUR-Lab/MuSR
|
| 194 |
+
args:
|
| 195 |
+
num_few_shot: 0
|
| 196 |
+
metrics:
|
| 197 |
+
- type: acc_norm
|
| 198 |
+
value: 5.07
|
| 199 |
+
name: acc_norm
|
| 200 |
+
source:
|
| 201 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Locutusque/TinyMistral-248M-v2.5
|
| 202 |
+
name: Open LLM Leaderboard
|
| 203 |
+
- task:
|
| 204 |
+
type: text-generation
|
| 205 |
+
name: Text Generation
|
| 206 |
+
dataset:
|
| 207 |
+
name: MMLU-PRO (5-shot)
|
| 208 |
+
type: TIGER-Lab/MMLU-Pro
|
| 209 |
+
config: main
|
| 210 |
+
split: test
|
| 211 |
+
args:
|
| 212 |
+
num_few_shot: 5
|
| 213 |
+
metrics:
|
| 214 |
+
- type: acc
|
| 215 |
+
value: 1.5
|
| 216 |
+
name: accuracy
|
| 217 |
+
source:
|
| 218 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Locutusque/TinyMistral-248M-v2.5
|
| 219 |
+
name: Open LLM Leaderboard
|
| 220 |
+
---
|
| 221 |
+
|
| 222 |
+
# ysn-rfd/TinyMistral-248M-v2.5-GGUF
|
| 223 |
+
This model was converted to GGUF format from [`Locutusque/TinyMistral-248M-v2.5`](https://huggingface.co/Locutusque/TinyMistral-248M-v2.5) using llama.cpp via the ggml.ai's [all-gguf-same-where](https://huggingface.co/spaces/matrixportal/all-gguf-same-where) space.
|
| 224 |
+
Refer to the [original model card](https://huggingface.co/Locutusque/TinyMistral-248M-v2.5) for more details on the model.
|
| 225 |
+
|
| 226 |
+
## ✅ Quantized Models Download List
|
| 227 |
+
|
| 228 |
+
### 🔍 Recommended Quantizations
|
| 229 |
+
- **✨ General CPU Use:** [`Q4_K_M`](https://huggingface.co/ysn-rfd/TinyMistral-248M-v2.5-GGUF/resolve/main/tinymistral-248m-v2.5-q4_k_m.gguf) (Best balance of speed/quality)
|
| 230 |
+
- **📱 ARM Devices:** [`Q4_0`](https://huggingface.co/ysn-rfd/TinyMistral-248M-v2.5-GGUF/resolve/main/tinymistral-248m-v2.5-q4_0.gguf) (Optimized for ARM CPUs)
|
| 231 |
+
- **🏆 Maximum Quality:** [`Q8_0`](https://huggingface.co/ysn-rfd/TinyMistral-248M-v2.5-GGUF/resolve/main/tinymistral-248m-v2.5-q8_0.gguf) (Near-original quality)
|
| 232 |
+
|
| 233 |
+
### 📦 Full Quantization Options
|
| 234 |
+
| 🚀 Download | 🔢 Type | 📝 Notes |
|
| 235 |
+
|:---------|:-----|:------|
|
| 236 |
+
| [Download](https://huggingface.co/ysn-rfd/TinyMistral-248M-v2.5-GGUF/resolve/main/tinymistral-248m-v2.5-q2_k.gguf) |  | Basic quantization |
|
| 237 |
+
| [Download](https://huggingface.co/ysn-rfd/TinyMistral-248M-v2.5-GGUF/resolve/main/tinymistral-248m-v2.5-q3_k_s.gguf) |  | Small size |
|
| 238 |
+
| [Download](https://huggingface.co/ysn-rfd/TinyMistral-248M-v2.5-GGUF/resolve/main/tinymistral-248m-v2.5-q3_k_m.gguf) |  | Balanced quality |
|
| 239 |
+
| [Download](https://huggingface.co/ysn-rfd/TinyMistral-248M-v2.5-GGUF/resolve/main/tinymistral-248m-v2.5-q3_k_l.gguf) |  | Better quality |
|
| 240 |
+
| [Download](https://huggingface.co/ysn-rfd/TinyMistral-248M-v2.5-GGUF/resolve/main/tinymistral-248m-v2.5-q4_0.gguf) |  | Fast on ARM |
|
| 241 |
+
| [Download](https://huggingface.co/ysn-rfd/TinyMistral-248M-v2.5-GGUF/resolve/main/tinymistral-248m-v2.5-q4_k_s.gguf) |  | Fast, recommended |
|
| 242 |
+
| [Download](https://huggingface.co/ysn-rfd/TinyMistral-248M-v2.5-GGUF/resolve/main/tinymistral-248m-v2.5-q4_k_m.gguf) |  ⭐ | Best balance |
|
| 243 |
+
| [Download](https://huggingface.co/ysn-rfd/TinyMistral-248M-v2.5-GGUF/resolve/main/tinymistral-248m-v2.5-q5_0.gguf) |  | Good quality |
|
| 244 |
+
| [Download](https://huggingface.co/ysn-rfd/TinyMistral-248M-v2.5-GGUF/resolve/main/tinymistral-248m-v2.5-q5_k_s.gguf) |  | Balanced |
|
| 245 |
+
| [Download](https://huggingface.co/ysn-rfd/TinyMistral-248M-v2.5-GGUF/resolve/main/tinymistral-248m-v2.5-q5_k_m.gguf) |  | High quality |
|
| 246 |
+
| [Download](https://huggingface.co/ysn-rfd/TinyMistral-248M-v2.5-GGUF/resolve/main/tinymistral-248m-v2.5-q6_k.gguf) |  🏆 | Very good quality |
|
| 247 |
+
| [Download](https://huggingface.co/ysn-rfd/TinyMistral-248M-v2.5-GGUF/resolve/main/tinymistral-248m-v2.5-q8_0.gguf) |  ⚡ | Fast, best quality |
|
| 248 |
+
| [Download](https://huggingface.co/ysn-rfd/TinyMistral-248M-v2.5-GGUF/resolve/main/tinymistral-248m-v2.5-f16.gguf) |  | Maximum accuracy |
|
| 249 |
+
|
| 250 |
+
💡 **Tip:** Use `F16` for maximum precision when quality is critical
|
| 251 |
+
|
| 252 |
+
|
| 253 |
+
---
|
| 254 |
+
# 🚀 Applications and Tools for Locally Quantized LLMs
|
| 255 |
+
## 🖥️ Desktop Applications
|
| 256 |
+
|
| 257 |
+
| Application | Description | Download Link |
|
| 258 |
+
|-----------------|----------------------------------------------------------------------------------------------|--------------------------------------------------------------------------------|
|
| 259 |
+
| **Llama.cpp** | A fast and efficient inference engine for GGUF models. | [GitHub Repository](https://github.com/ggml-org/llama.cpp) |
|
| 260 |
+
| **Ollama** | A streamlined solution for running LLMs locally. | [Website](https://ollama.com/) |
|
| 261 |
+
| **AnythingLLM** | An AI-powered knowledge management tool. | [GitHub Repository](https://github.com/Mintplex-Labs/anything-llm) |
|
| 262 |
+
| **Open WebUI** | A user-friendly web interface for running local LLMs. | [GitHub Repository](https://github.com/open-webui/open-webui) |
|
| 263 |
+
| **GPT4All** | A user-friendly desktop application supporting various LLMs, compatible with GGUF models. | [GitHub Repository](https://github.com/nomic-ai/gpt4all) |
|
| 264 |
+
| **LM Studio** | A desktop application designed to run and manage local LLMs, supporting GGUF format. | [Website](https://lmstudio.ai/) |
|
| 265 |
+
| **GPT4All Chat**| A chat application compatible with GGUF models for local, offline interactions. | [GitHub Repository](https://github.com/nomic-ai/gpt4all) |
|
| 266 |
+
|
| 267 |
+
---
|
| 268 |
+
|
| 269 |
+
## 📱 Mobile Applications
|
| 270 |
+
|
| 271 |
+
| Application | Description | Download Link |
|
| 272 |
+
|-------------------|----------------------------------------------------------------------------------------------|--------------------------------------------------------------------------------|
|
| 273 |
+
| **ChatterUI** | A simple and lightweight LLM app for mobile devices. | [GitHub Repository](https://github.com/Vali-98/ChatterUI) |
|
| 274 |
+
| **Maid** | Mobile Artificial Intelligence Distribution for running AI models on mobile devices. | [GitHub Repository](https://github.com/Mobile-Artificial-Intelligence/maid) |
|
| 275 |
+
| **PocketPal AI** | A mobile AI assistant powered by local models. | [GitHub Repository](https://github.com/a-ghorbani/pocketpal-ai) |
|
| 276 |
+
| **Layla** | A flexible platform for running various AI models on mobile devices. | [Website](https://www.layla-network.ai/) |
|
| 277 |
+
|
| 278 |
+
---
|
| 279 |
+
|
| 280 |
+
## 🎨 Image Generation Applications
|
| 281 |
+
|
| 282 |
+
| Application | Description | Download Link |
|
| 283 |
+
|-------------------------------------|----------------------------------------------------------------------------------------------|--------------------------------------------------------------------------------|
|
| 284 |
+
| **Stable Diffusion** | An open-source AI model for generating images from text. | [GitHub Repository](https://github.com/CompVis/stable-diffusion) |
|
| 285 |
+
| **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) |
|
| 286 |
+
| **Local Dream** | Android Stable Diffusion with Snapdragon NPU acceleration. Also supports CPU inference. | [GitHub Repository](https://github.com/xororz/local-dream) |
|
| 287 |
+
| **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) |
|
| 288 |
+
|
| 289 |
+
---
|
| 290 |
+
|