There may be a problem with this model transformation, and the model's intelligence is behaving abnormally.
Provided files
| Name | Quant method | Size |
|---|---|---|
| baichuan2-13b-chat.Q4_0.gguf | Q4_0 | 7.4 GB |
| baichuan2-13b-chat.Q4_1.gguf | Q4_1 | 8.2 GB |
| baichuan2-13b-chat.Q5_0.gguf | Q5_0 | 9.0 GB |
| baichuan2-13b-chat.Q5_1.gguf | Q5_1 | 9.8 GB |
| baichuan2-13b-chat.Q8_0.gguf | Q8_0 | 14 GB |
| baichuan2-13b-chat.gguf | full | 26 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/baichuan2-13b-chat-gguf:Q4_0 |
Q4_0 | 7.44 GB |
shaowenchen/baichuan2-13b-chat-gguf:Q4_1 |
Q4_1 | 8.27 GB |
shaowenchen/baichuan2-13b-chat-gguf:Q5_0 |
Q5_0 | 9.29 GB |
shaowenchen/baichuan2-13b-chat-gguf:Q5_1 |
Q5_1 | 10 GB |
shaowenchen/baichuan2-13b-chat-gguf:Q8_0 |
Q8_0 | 13.6 GB |
shaowenchen/baichuan2-13b-chat-gguf:full |
full | 20.12 GB |
Usage:
docker run --rm -p 8000:8000 shaowenchen/baichuan2-13b-chat-gguf:Q4_0
and you can view http://localhost:8000/docs to see the swagger UI.