Provided files
| Name | Quant method | Size |
|---|---|---|
| longchat-7b-v1.5-32k.Q2_K.gguf | Q2_K | 5.1 GB |
| longchat-7b-v1.5-32k.Q3_K.gguf | Q3_K | 5.9 GB |
| longchat-7b-v1.5-32k.Q3KL.gguf | Q3KL | 6.5 GB |
| longchat-7b-v1.5-32k.Q3KS.gguf | Q3KS | 5.3 GB |
| longchat-7b-v1.5-32k.Q4_0.gguf | Q4_0 | 6.9 GB |
| longchat-7b-v1.5-32k.Q4_1.gguf | Q4_1 | 7.6 GB |
| longchat-7b-v1.5-32k.Q4_K.gguf | Q4_K | 7.3 GB |
| longchat-7b-v1.5-32k.Q4KS.gguf | Q4KS | 6.9 GB |
| longchat-7b-v1.5-32k.Q5_0.gguf | Q5_0 | 8.4 GB |
| longchat-7b-v1.5-32k.Q5_1.gguf | Q5_1 | 9.1 GB |
| longchat-7b-v1.5-32k.Q5_K.gguf | Q5_K | 8.6 GB |
| longchat-7b-v1.5-32k.Q5KS.gguf | Q5KS | 8.4 GB |
| longchat-7b-v1.5-32k.Q6_K.gguf | Q6_K | 9.9 GB |
| longchat-7b-v1.5-32k.Q8_0.gguf | Q8_0 | 13 GB |
| longchat-7b-v1.5-32k.gguf | full | 24 GB |
Usage:
docker run --rm -it -p 8000:8000 -v /path/to/models:/models -e MODEL=/models/gguf-model-name.gguf hubimage/llama-cpp-python:latest
and you can view http://localhost:8000/docs to see the swagger UI.
Provided images
| Name | Quant method | Compressed Size |
|---|---|---|
shaowenchen/longchat-7b-v1.5-32k-gguf:Q2_K |
Q2_K | 2.88 GB |
shaowenchen/longchat-7b-v1.5-32k-gguf:Q3_K |
Q3_K | 3.3 GB |
shaowenchen/longchat-7b-v1.5-32k-gguf:Q4_K |
Q4_K | 4 GB |
Usage:
docker run --rm -p 8000:8000 shaowenchen/longchat-7b-v1.5-32k-gguf:Q2_K
and you can view http://localhost:8000/docs to see the swagger UI.
评论