Hugging Face's logo

ysn-rfd
/
BabyMistral-GGUF

Text Generation
Transformers
GGUF
English
llama-cpp
matrixportal
conversational
Model card Files
xet
Community
ysn-rfd commited on
Commit
61850c0
·
verified ·
1 Parent(s): 346a46e

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +22 -41
README.md CHANGED
@@ -7,49 +7,30 @@ license: apache-2.0
7
  pipeline_tag: text-generation
8
  tags:
9
  - llama-cpp
10
- - gguf-my-repo
11
  ---
12
 
13
  # ysn-rfd/BabyMistral-GGUF
14
- This model was converted to GGUF format from [`OEvortex/BabyMistral`](https://huggingface.co/OEvortex/BabyMistral) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
15
  Refer to the [original model card](https://huggingface.co/OEvortex/BabyMistral) for more details on the model.
16
 
17
- ## Use with llama.cpp
18
- Install llama.cpp through brew (works on Mac and Linux)
19
-
20
- ```bash
21
- brew install llama.cpp
22
-
23
- ```
24
- Invoke the llama.cpp server or the CLI.
25
-
26
- ### CLI:
27
- ```bash
28
- llama-cli --hf-repo ysn-rfd/BabyMistral-GGUF --hf-file babymistral-q5_0.gguf -p "The meaning to life and the universe is"
29
- ```
30
-
31
- ### Server:
32
- ```bash
33
- llama-server --hf-repo ysn-rfd/BabyMistral-GGUF --hf-file babymistral-q5_0.gguf -c 2048
34
- ```
35
-
36
- Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
37
-
38
- Step 1: Clone llama.cpp from GitHub.
39
- ```
40
- git clone https://github.com/ggerganov/llama.cpp
41
- ```
42
-
43
- Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
44
- ```
45
- cd llama.cpp && LLAMA_CURL=1 make
46
- ```
47
-
48
- Step 3: Run inference through the main binary.
49
- ```
50
- ./llama-cli --hf-repo ysn-rfd/BabyMistral-GGUF --hf-file babymistral-q5_0.gguf -p "The meaning to life and the universe is"
51
- ```
52
- or
53
- ```
54
- ./llama-server --hf-repo ysn-rfd/BabyMistral-GGUF --hf-file babymistral-q5_0.gguf -c 2048
55
- ```
 
7
  pipeline_tag: text-generation
8
  tags:
9
  - llama-cpp
10
+ - matrixportal
11
  ---
12
 
13
  # ysn-rfd/BabyMistral-GGUF
14
+ This model was converted to GGUF format from [`OEvortex/BabyMistral`](https://huggingface.co/OEvortex/BabyMistral) using llama.cpp via the ggml.ai's [all-gguf-same-where](https://huggingface.co/spaces/matrixportal/all-gguf-same-where) space.
15
  Refer to the [original model card](https://huggingface.co/OEvortex/BabyMistral) for more details on the model.
16
 
17
+ ## ✅ Quantized Models Download List
18
+ **✨ Recommended for CPU:** `Q4_K_M` | **⚡ Recommended for ARM CPU:** `Q4_0` | **🏆 Best Quality:** `Q8_0`
19
+
20
+ | 🚀 Download | 🔢 Type | 📝 Notes |
21
+ |:---------|:-----|:------|
22
+ | [Download](https://huggingface.co/ysn-rfd/BabyMistral-GGUF/resolve/main/babymistral-q2_k.gguf) | ![Q2_K](https://img.shields.io/badge/Q2_K-1A73E8) | Basic quantization |
23
+ | [Download](https://huggingface.co/ysn-rfd/BabyMistral-GGUF/resolve/main/babymistral-q3_k_s.gguf) | ![Q3_K_S](https://img.shields.io/badge/Q3_K_S-34A853) | Small size |
24
+ | [Download](https://huggingface.co/ysn-rfd/BabyMistral-GGUF/resolve/main/babymistral-q3_k_m.gguf) | ![Q3_K_M](https://img.shields.io/badge/Q3_K_M-FBBC05) | Balanced quality |
25
+ | [Download](https://huggingface.co/ysn-rfd/BabyMistral-GGUF/resolve/main/babymistral-q3_k_l.gguf) | ![Q3_K_L](https://img.shields.io/badge/Q3_K_L-4285F4) | Better quality |
26
+ | [Download](https://huggingface.co/ysn-rfd/BabyMistral-GGUF/resolve/main/babymistral-q4_0.gguf) | ![Q4_0](https://img.shields.io/badge/Q4_0-EA4335) | Fast on ARM |
27
+ | [Download](https://huggingface.co/ysn-rfd/BabyMistral-GGUF/resolve/main/babymistral-q4_k_s.gguf) | ![Q4_K_S](https://img.shields.io/badge/Q4_K_S-673AB7) | Fast, recommended |
28
+ | [Download](https://huggingface.co/ysn-rfd/BabyMistral-GGUF/resolve/main/babymistral-q4_k_m.gguf) | ![Q4_K_M](https://img.shields.io/badge/Q4_K_M-673AB7) ⭐ | Best balance |
29
+ | [Download](https://huggingface.co/ysn-rfd/BabyMistral-GGUF/resolve/main/babymistral-q5_0.gguf) | ![Q5_0](https://img.shields.io/badge/Q5_0-FF6D01) | Good quality |
30
+ | [Download](https://huggingface.co/ysn-rfd/BabyMistral-GGUF/resolve/main/babymistral-q5_k_s.gguf) | ![Q5_K_S](https://img.shields.io/badge/Q5_K_S-0F9D58) | Balanced |
31
+ | [Download](https://huggingface.co/ysn-rfd/BabyMistral-GGUF/resolve/main/babymistral-q5_k_m.gguf) | ![Q5_K_M](https://img.shields.io/badge/Q5_K_M-0F9D58) | High quality |
32
+ | [Download](https://huggingface.co/ysn-rfd/BabyMistral-GGUF/resolve/main/babymistral-q6_k.gguf) | ![Q6_K](https://img.shields.io/badge/Q6_K-4285F4) 🏆 | Very good quality |
33
+ | [Download](https://huggingface.co/ysn-rfd/BabyMistral-GGUF/resolve/main/babymistral-q8_0.gguf) | ![Q8_0](https://img.shields.io/badge/Q8_0-EA4335) ⚡ | Fast, best quality |
34
+ | [Download](https://huggingface.co/ysn-rfd/BabyMistral-GGUF/resolve/main/babymistral-f16.gguf) | ![F16](https://img.shields.io/badge/F16-000000) | Maximum accuracy |
35
+
36
+ 💡 **Tip:** Use `F16` for maximum precision when quality is critical