metadata
inference: false
language:
- zh
license: other
model_creator: ziqingyang
model_link: https://huggingface.co/ziqingyang/chinese-llama-2-13b-16k
model_name: chinese-llama-2-13b-16k
model_type: llama
pipeline_tag: text-generation
quantized_by: shaowenchen
tasks:
- text2text-generation
tags:
- meta
- gguf
- llama
- llama-2
- chinese
Provided files
| Name | Quant method | Size |
|---|---|---|
| chinese-llama-2-13b-16k.Q2_K.gguf | Q2_K | 5.2 G |
| chinese-llama-2-13b-16k.Q3_K.gguf | Q3_K | 6.0 G |
| chinese-llama-2-13b-16k.Q3_K_L.gguf | Q3_K_L | 6.6 G |
| chinese-llama-2-13b-16k.Q3_K_S.gguf | Q3_K_S | 5.4 G |
| chinese-llama-2-13b-16k.Q4_0.gguf | Q4_0 | 7.0 G |
| chinese-llama-2-13b-16k.Q4_1.gguf | Q4_1 | 7.8 G |
| chinese-llama-2-13b-16k.Q4_K.gguf | Q4_K | 7.5 G |
| chinese-llama-2-13b-16k.Q4_K_S.gguf | Q4_K_S | 7.1 G |
| chinese-llama-2-13b-16k.Q5_0.gguf | Q5_0 | 8.5 G |
| chinese-llama-2-13b-16k.Q5_1.gguf | Q5_1 | 9.3 G |
| chinese-llama-2-13b-16k.Q5_K.gguf | Q5_K | 8.8 G |
| chinese-llama-2-13b-16k.Q5_K_S.gguf | Q5_K_S | 8.5 G |
| chinese-llama-2-13b-16k.Q6_K.gguf | Q6_K | 10 G |
| chinese-llama-2-13b-16k.Q8_0.gguf | Q8_0 | 13 G |
| chinese-llama-2-13b-16k.gguf | full | 25 G |
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.