Provided files
| Name | Quant method | Size |
|---|---|---|
| chinese-llama-2-13b.Q2_K.gguf | Q2_K | 5.2 GB |
| chinese-llama-2-13b.Q3_K.gguf | Q3_K | 6.0 GB |
| chinese-llama-2-13b.Q3KL.gguf | Q3KL | 6.6 GB |
| chinese-llama-2-13b.Q3KS.gguf | Q3KS | 5.4 GB |
| chinese-llama-2-13b.Q4_0.gguf | Q4_0 | 7.0 GB |
| chinese-llama-2-13b.Q4_1.gguf | Q4_1 | 7.8 GB |
| chinese-llama-2-13b.Q4_K.gguf | Q4_K | 7.5 GB |
| chinese-llama-2-13b.Q4KS.gguf | Q4KS | 7.1 GB |
| chinese-llama-2-13b.Q5_0.gguf | Q5_0 | 8.5 GB |
| chinese-llama-2-13b.Q5_1.gguf | Q5_1 | 9.3 GB |
| chinese-llama-2-13b.Q5_K.gguf | Q5_K | 8.8 GB |
| chinese-llama-2-13b.Q5KS.gguf | Q5KS | 8.5 GB |
| chinese-llama-2-13b.Q6_K.gguf | Q6_K | 10 GB |
| chinese-llama-2-13b.Q8_0.gguf | Q8_0 | 13 GB |
| chinese-llama-2-13b.gguf | full | 25 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.
评论