metadata
inference: false
language:
- zh
license: apache-2.0
model_creator: ziqingyang
model_link: https://www.modelscope.cn/ziqingyang/chinese-llama-2-7b
model_name: chinese-llama-2-7b
model_type: llama
pipeline_tag: text-generation
quantized_by: shaowenchen
tags:
- meta
- gguf
- llama
- llama-2
- chinese
English | 中文
提供的文件
| 名称 | 量化方法 | 大小 |
|---|---|---|
| chinese-llama-2-7b.Q2_K.gguf | Q2_K | 2.7 GB |
| chinese-llama-2-7b.Q3_K.gguf | Q3_K | 3.2 GB |
| chinese-llama-2-7b.Q3_K_L.gguf | Q3_K_L | 3.5 GB |
| chinese-llama-2-7b.Q3_K_S.gguf | Q3_K_S | 2.9 GB |
| chinese-llama-2-7b.Q4_0.gguf | Q4_0 | 3.7 GB |
| chinese-llama-2-7b.Q4_1.gguf | Q4_1 | 4.1 GB |
| chinese-llama-2-7b.Q4_K.gguf | Q4_K | 3.9 GB |
| chinese-llama-2-7b.Q4_K_S.gguf | Q4_K_S | 3.7 GB |
| chinese-llama-2-7b.Q5_0.gguf | Q5_0 | 4.5 GB |
| chinese-llama-2-7b.Q5_1.gguf | Q5_1 | 4.9 GB |
| chinese-llama-2-7b.Q5_K.gguf | Q5_K | 4.6 GB |
| chinese-llama-2-7b.Q5_K_S.gguf | Q5_K_S | 4.5 GB |
| chinese-llama-2-7b.Q6_K.gguf | Q6_K | 5.3 GB |
| chinese-llama-2-7b.Q8_0.gguf | Q8_0 | 6.9 GB |
| chinese-llama-2-7b.gguf | 完整 | 13 GB |
提供的镜像
| 名称 | 量化方法 | 大小 |
|---|---|---|
| shaowenchen/chinese-llama-2-7b-gguf:Q2_K | Q2_K | 3.68 GB |
| shaowenchen/chinese-llama-2-7b-gguf:Q3_K | Q3_K | 4.16 GB |
| shaowenchen/chinese-llama-2-7b-gguf:Q3_K_L | Q3_K_L | 4.46 GB |
| shaowenchen/chinese-llama-2-7b-gguf:Q3_K_S | Q3_K_S | 3.81 GB |
| shaowenchen/chinese-llama-2-7b-gguf:Q4_0 | Q4_0 | 4.7 GB |
| shaowenchen/chinese-llama-2-7b-gguf:Q4_K | Q4_K | 4.95 GB |
| shaowenchen/chinese-llama-2-7b-gguf:Q4_K_S | Q4_K_S | 4.73 GB |
docker run --rm -p 8000:8000 shaowenchen/chinese-llama-2-7b-gguf:Q2_K
并打开 http://localhost:8000/docs 查看 API 文档。