Feedback and support: TensorBlock's Twitter/X, Telegram Group and Discord server
luaqi/sn29_v31 - GGUF
This repo contains GGUF format model files for luaqi/sn29_v31.
The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4011.
Prompt template
<|system|>
{system_prompt}<|end|>
<|user|>
{prompt}<|end|>
<|assistant|>
Model file specification
Filename | Quant type | File Size | Description |
---|---|---|---|
sn29_v31-Q2_K.gguf | Q2_K | 1.925 GB | smallest, significant quality loss - not recommended for most purposes |
sn29_v31-Q3_K_S.gguf | Q3_K_S | 2.292 GB | very small, high quality loss |
sn29_v31-Q3_K_M.gguf | Q3_K_M | 2.674 GB | very small, high quality loss |
sn29_v31-Q3_K_L.gguf | Q3_K_L | 2.859 GB | small, substantial quality loss |
sn29_v31-Q4_0.gguf | Q4_0 | 2.976 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
sn29_v31-Q4_K_S.gguf | Q4_K_S | 2.994 GB | small, greater quality loss |
sn29_v31-Q4_K_M.gguf | Q4_K_M | 3.280 GB | medium, balanced quality - recommended |
sn29_v31-Q5_0.gguf | Q5_0 | 3.621 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
sn29_v31-Q5_K_S.gguf | Q5_K_S | 3.621 GB | large, low quality loss - recommended |
sn29_v31-Q5_K_M.gguf | Q5_K_M | 3.863 GB | large, very low quality loss - recommended |
sn29_v31-Q6_K.gguf | Q6_K | 4.305 GB | very large, extremely low quality loss |
sn29_v31-Q8_0.gguf | Q8_0 | 5.576 GB | very large, extremely low quality loss - not recommended |
Downloading instruction
Command line
Firstly, install Huggingface Client
pip install -U "huggingface_hub[cli]"
Then, downoad the individual model file the a local directory
huggingface-cli download tensorblock/sn29_v31-GGUF --include "sn29_v31-Q2_K.gguf" --local-dir MY_LOCAL_DIR
If you wanna download multiple model files with a pattern (e.g., *Q4_K*gguf
), you can try:
huggingface-cli download tensorblock/sn29_v31-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
- Downloads last month
- 70
Model tree for tensorblock/sn29_v31-GGUF
Base model
luaqi/sn29_v31