metadata
inference: true
language:
- zh
- en
license: other
model_creator: lmsys
model_link: https://huggingface.co/lmsys/vicuna-13b-v1.5-16k
model_name: vicuna-13b-v1.5-16k
model_type: vicuna
pipeline_tag: text-generation
quantized_by: shaowenchen
tasks:
- text2text-generation
tags:
- gguf
- vicuna
- chinese
Provided files
| Name | Quant method | Size |
|---|---|---|
| vicuna-13b-v1.5-16k.Q2_K.gguf | Q2_K | 5.1 GB |
| vicuna-13b-v1.5-16k.Q3_K.gguf | Q3_K | 5.9 GB |
| vicuna-13b-v1.5-16k.Q3_K_L.gguf | Q3_K_L | 6.5 GB |
| vicuna-13b-v1.5-16k.Q3_K_S.gguf | Q3_K_S | 5.3 GB |
| vicuna-13b-v1.5-16k.Q4_0.gguf | Q4_0 | 6.9 GB |
| vicuna-13b-v1.5-16k.Q4_1.gguf | Q4_1 | 7.6 GB |
| vicuna-13b-v1.5-16k.Q4_K.gguf | Q4_K | 7.3 GB |
| vicuna-13b-v1.5-16k.Q4_K_S.gguf | Q4_K_S | 6.9 GB |
| vicuna-13b-v1.5-16k.Q5_0.gguf | Q5_0 | 8.4 GB |
| vicuna-13b-v1.5-16k.Q5_1.gguf | Q5_1 | 9.1 GB |
| vicuna-13b-v1.5-16k.Q5_K.gguf | Q5_K | 8.6 GB |
| vicuna-13b-v1.5-16k.Q5_K_S.gguf | Q5_K_S | 8.4 GB |
| vicuna-13b-v1.5-16k.Q6_K.gguf | Q6_K | 9.9 GB |
| vicuna-13b-v1.5-16k.Q8_0.gguf | Q8_0 | 13 GB |
| vicuna-13b-v1.5-16k.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/vicuna-13b-v1.5-16k-gguf:Q2_K |
Q2_K | 5.29 GB |
shaowenchen/vicuna-13b-v1.5-16k-gguf:Q3_K |
Q3_K | 6.11 GB |
shaowenchen/vicuna-13b-v1.5-16k-gguf:Q4_K |
Q4_K | 7.47 GB |
Usage:
docker run --rm -p 8000:8000 shaowenchen/vicuna-13b-v1.5-16k-gguf:Q2_K
and you can view http://localhost:8000/docs to see the swagger UI.