Commit
•
2f571d8
1
Parent(s):
cad12a3
fix meta json
Browse files- README.md +32 -30
- README_zh.md +0 -58
- configuration.json +3 -0
README.md
CHANGED
|
@@ -2,13 +2,15 @@
|
|
| 2 |
inference: false
|
| 3 |
language:
|
| 4 |
- zh
|
| 5 |
-
license:
|
| 6 |
model_creator: ziqingyang
|
| 7 |
model_link: https://huggingface.co/ziqingyang/chinese-llama-2-7b-16k
|
| 8 |
model_name: chinese-llama-2-7b-16k
|
| 9 |
model_type: llama
|
| 10 |
pipeline_tag: text-generation
|
| 11 |
quantized_by: shaowenchen
|
|
|
|
|
|
|
| 12 |
tags:
|
| 13 |
- meta
|
| 14 |
- gguf
|
|
@@ -17,42 +19,42 @@ tags:
|
|
| 17 |
- chinese
|
| 18 |
---
|
| 19 |
|
| 20 |
-
> English | [中文](README_zh.md)
|
| 21 |
-
|
| 22 |
## Provided files
|
| 23 |
|
| 24 |
-
| Name
|
| 25 |
-
|
|
| 26 |
-
|
|
| 27 |
-
|
|
| 28 |
-
|
|
| 29 |
-
|
|
| 30 |
-
|
|
| 31 |
-
|
|
| 32 |
-
|
|
| 33 |
-
|
|
| 34 |
-
|
|
| 35 |
-
|
|
| 36 |
-
|
|
| 37 |
-
|
|
| 38 |
-
|
|
| 39 |
-
|
|
| 40 |
-
|
|
| 41 |
|
| 42 |
## Provided images
|
| 43 |
|
| 44 |
-
| Name
|
| 45 |
-
|
|
| 46 |
-
|
|
| 47 |
-
|
|
| 48 |
-
|
|
| 49 |
-
|
|
| 50 |
-
|
|
| 51 |
-
|
|
| 52 |
-
|
|
|
|
|
|
|
|
| 53 |
|
| 54 |
```
|
| 55 |
docker run --rm -p 8000:8000 shaowenchen/chinese-llama-2-7b-16k-gguf:Q2_K
|
| 56 |
```
|
| 57 |
|
| 58 |
-
and
|
|
|
|
| 2 |
inference: false
|
| 3 |
language:
|
| 4 |
- zh
|
| 5 |
+
license: other
|
| 6 |
model_creator: ziqingyang
|
| 7 |
model_link: https://huggingface.co/ziqingyang/chinese-llama-2-7b-16k
|
| 8 |
model_name: chinese-llama-2-7b-16k
|
| 9 |
model_type: llama
|
| 10 |
pipeline_tag: text-generation
|
| 11 |
quantized_by: shaowenchen
|
| 12 |
+
tasks:
|
| 13 |
+
- text2text-generation
|
| 14 |
tags:
|
| 15 |
- meta
|
| 16 |
- gguf
|
|
|
|
| 19 |
- chinese
|
| 20 |
---
|
| 21 |
|
|
|
|
|
|
|
| 22 |
## Provided files
|
| 23 |
|
| 24 |
+
| Name | Quant method | Size |
|
| 25 |
+
| ---------------------------------- | ------------ | ------ |
|
| 26 |
+
| chinese-llama-2-7b-16k.Q2_K.gguf | Q2_K | 2.7 GB |
|
| 27 |
+
| chinese-llama-2-7b-16k.Q3_K.gguf | Q3_K | 3.2 GB |
|
| 28 |
+
| chinese-llama-2-7b-16k.Q3_K_L.gguf | Q3_K_L | 3.5 GB |
|
| 29 |
+
| chinese-llama-2-7b-16k.Q3_K_S.gguf | Q3_K_S | 2.9 GB |
|
| 30 |
+
| chinese-llama-2-7b-16k.Q4_0.gguf | Q4_0 | 3.7 GB |
|
| 31 |
+
| chinese-llama-2-7b-16k.Q4_1.gguf | Q4_1 | 4.1 GB |
|
| 32 |
+
| chinese-llama-2-7b-16k.Q4_K.gguf | Q4_K | 3.9 GB |
|
| 33 |
+
| chinese-llama-2-7b-16k.Q4_K_S.gguf | Q4_K_S | 3.7 GB |
|
| 34 |
+
| chinese-llama-2-7b-16k.Q5_0.gguf | Q5_0 | 4.5 GB |
|
| 35 |
+
| chinese-llama-2-7b-16k.Q5_1.gguf | Q5_1 | 4.9 GB |
|
| 36 |
+
| chinese-llama-2-7b-16k.Q5_K.gguf | Q5_K | 4.6 GB |
|
| 37 |
+
| chinese-llama-2-7b-16k.Q5_K_S.gguf | Q5_K_S | 4.5 GB |
|
| 38 |
+
| chinese-llama-2-7b-16k.Q6_K.gguf | Q6_K | 5.3 GB |
|
| 39 |
+
| chinese-llama-2-7b-16k.Q8_0.gguf | Q8_0 | 6.9 GB |
|
| 40 |
+
| chinese-llama-2-7b-16k.gguf | full | 13 GB |
|
| 41 |
|
| 42 |
## Provided images
|
| 43 |
|
| 44 |
+
| Name | Quant method | Size |
|
| 45 |
+
| ---------------------------------------------- | ------------ | ------- |
|
| 46 |
+
| shaowenchen/chinese-llama-2-7b-16k-gguf:Q2_K | Q2_K | 3.68 GB |
|
| 47 |
+
| shaowenchen/chinese-llama-2-7b-16k-gguf:Q3_K | Q3_K | 4.16 GB |
|
| 48 |
+
| shaowenchen/chinese-llama-2-7b-16k-gguf:Q3_K_L | Q3_K_L | 4.46 GB |
|
| 49 |
+
| shaowenchen/chinese-llama-2-7b-16k-gguf:Q3_K_S | Q3_K_S | 3.81 GB |
|
| 50 |
+
| shaowenchen/chinese-llama-2-7b-16k-gguf:Q4_0 | Q4_0 | 4.7 GB |
|
| 51 |
+
| shaowenchen/chinese-llama-2-7b-16k-gguf:Q4_K | Q4_K | 4.95 GB |
|
| 52 |
+
| shaowenchen/chinese-llama-2-7b-16k-gguf:Q4_K_S | Q4_K_S | 4.73 GB |
|
| 53 |
+
|
| 54 |
+
Usage:
|
| 55 |
|
| 56 |
```
|
| 57 |
docker run --rm -p 8000:8000 shaowenchen/chinese-llama-2-7b-16k-gguf:Q2_K
|
| 58 |
```
|
| 59 |
|
| 60 |
+
and you can view http://localhost:8000/docs to see the swagger UI.
|
README_zh.md
DELETED
|
@@ -1,58 +0,0 @@
|
|
| 1 |
-
---
|
| 2 |
-
inference: false
|
| 3 |
-
language:
|
| 4 |
-
- zh
|
| 5 |
-
license: apache-2.0
|
| 6 |
-
model_creator: ziqingyang
|
| 7 |
-
model_link: https://huggingface.co/ziqingyang/chinese-llama-2-7b-16k
|
| 8 |
-
model_name: chinese-llama-2-7b-16k
|
| 9 |
-
model_type: llama
|
| 10 |
-
pipeline_tag: text-generation
|
| 11 |
-
quantized_by: shaowenchen
|
| 12 |
-
tags:
|
| 13 |
-
- meta
|
| 14 |
-
- gguf
|
| 15 |
-
- llama
|
| 16 |
-
- llama-2
|
| 17 |
-
- chinese
|
| 18 |
-
---
|
| 19 |
-
|
| 20 |
-
> [English](README.md) | 中文
|
| 21 |
-
|
| 22 |
-
## 提供的文件
|
| 23 |
-
|
| 24 |
-
| 名称 | 量化方法 | 大小 |
|
| 25 |
-
| ---------------------------------------------------------------------------------------------------------------------------------------- | -------- | ------ |
|
| 26 |
-
| [chinese-llama-2-7b-16k.Q2_K.gguf](https://www.modelscope.cn/shaowenchen/chinese-llama-2-7b-16k-gguf/blob/main/chinese-llama-2-7b-16k.Q2_K.gguf) | Q2_K | 2.7 GB |
|
| 27 |
-
| [chinese-llama-2-7b-16k.Q3_K.gguf](https://www.modelscope.cn/shaowenchen/chinese-llama-2-7b-16k-gguf/blob/main/chinese-llama-2-7b-16k.Q3_K.gguf) | Q3_K | 3.2 GB |
|
| 28 |
-
| [chinese-llama-2-7b-16k.Q3_K_L.gguf](https://www.modelscope.cn/shaowenchen/chinese-llama-2-7b-16k-gguf/blob/main/chinese-llama-2-7b-16k.Q3_K_L.gguf) | Q3_K_L | 3.5 GB |
|
| 29 |
-
| [chinese-llama-2-7b-16k.Q3_K_S.gguf](https://www.modelscope.cn/shaowenchen/chinese-llama-2-7b-16k-gguf/blob/main/chinese-llama-2-7b-16k.Q3_K_S.gguf) | Q3_K_S | 2.9 GB |
|
| 30 |
-
| [chinese-llama-2-7b-16k.Q4_0.gguf](https://www.modelscope.cn/shaowenchen/chinese-llama-2-7b-16k-gguf/blob/main/chinese-llama-2-7b-16k.Q4_0.gguf) | Q4_0 | 3.7 GB |
|
| 31 |
-
| [chinese-llama-2-7b-16k.Q4_1.gguf](https://www.modelscope.cn/shaowenchen/chinese-llama-2-7b-16k-gguf/blob/main/chinese-llama-2-7b-16k.Q4_1.gguf) | Q4_1 | 4.1 GB |
|
| 32 |
-
| [chinese-llama-2-7b-16k.Q4_K.gguf](https://www.modelscope.cn/shaowenchen/chinese-llama-2-7b-16k-gguf/blob/main/chinese-llama-2-7b-16k.Q4_K.gguf) | Q4_K | 3.9 GB |
|
| 33 |
-
| [chinese-llama-2-7b-16k.Q4_K_S.gguf](https://www.modelscope.cn/shaowenchen/chinese-llama-2-7b-16k-gguf/blob/main/chinese-llama-2-7b-16k.Q4_K_S.gguf) | Q4_K_S | 3.7 GB |
|
| 34 |
-
| [chinese-llama-2-7b-16k.Q5_0.gguf](https://www.modelscope.cn/shaowenchen/chinese-llama-2-7b-16k-gguf/blob/main/chinese-llama-2-7b-16k.Q5_0.gguf) | Q5_0 | 4.5 GB |
|
| 35 |
-
| [chinese-llama-2-7b-16k.Q5_1.gguf](https://www.modelscope.cn/shaowenchen/chinese-llama-2-7b-16k-gguf/blob/main/chinese-llama-2-7b-16k.Q5_1.gguf) | Q5_1 | 4.9 GB |
|
| 36 |
-
| [chinese-llama-2-7b-16k.Q5_K.gguf](https://www.modelscope.cn/shaowenchen/chinese-llama-2-7b-16k-gguf/blob/main/chinese-llama-2-7b-16k.Q5_K.gguf) | Q5_K | 4.6 GB |
|
| 37 |
-
| [chinese-llama-2-7b-16k.Q5_K_S.gguf](https://www.modelscope.cn/shaowenchen/chinese-llama-2-7b-16k-gguf/blob/main/chinese-llama-2-7b-16k.Q5_K_S.gguf) | Q5_K_S | 4.5 GB |
|
| 38 |
-
| [chinese-llama-2-7b-16k.Q6_K.gguf](https://www.modelscope.cn/shaowenchen/chinese-llama-2-7b-16k-gguf/blob/main/chinese-llama-2-7b-16k.Q6_K.gguf) | Q6_K | 5.3 GB |
|
| 39 |
-
| [chinese-llama-2-7b-16k.Q8_0.gguf](https://www.modelscope.cn/shaowenchen/chinese-llama-2-7b-16k-gguf/blob/main/chinese-llama-2-7b-16k.Q8_0.gguf) | Q8_0 | 6.9 GB |
|
| 40 |
-
| [chinese-llama-2-7b-16k.gguf](https://www.modelscope.cn/shaowenchen/chinese-llama-2-7b-16k-gguf/blob/main/chinese-llama-2-7b-16k.gguf) | 完整 | 13 GB |
|
| 41 |
-
|
| 42 |
-
## 提供的镜像
|
| 43 |
-
|
| 44 |
-
| 名称 | 量化方法 | 大小 |
|
| 45 |
-
| ---------------------------------------------------------------------------------------------------------------------------------- | -------- | ------- |
|
| 46 |
-
| [shaowenchen/chinese-llama-2-7b-16k-gguf:Q2_K](https://hub.docker.com/repository/docker/shaowenchen/chinese-llama-2-7b-16k-gguf/general) | Q2_K | 3.68 GB |
|
| 47 |
-
| [shaowenchen/chinese-llama-2-7b-16k-gguf:Q3_K](https://hub.docker.com/repository/docker/shaowenchen/chinese-llama-2-7b-16k-gguf/general) | Q3_K | 4.16 GB |
|
| 48 |
-
| [shaowenchen/chinese-llama-2-7b-16k-gguf:Q3_K_L](https://hub.docker.com/repository/docker/shaowenchen/chinese-llama-2-7b-16k-gguf/general) | Q3_K_L | 4.46 GB |
|
| 49 |
-
| [shaowenchen/chinese-llama-2-7b-16k-gguf:Q3_K_S](https://hub.docker.com/repository/docker/shaowenchen/chinese-llama-2-7b-16k-gguf/general) | Q3_K_S | 3.81 GB |
|
| 50 |
-
| [shaowenchen/chinese-llama-2-7b-16k-gguf:Q4_0](https://hub.docker.com/repository/docker/shaowenchen/chinese-llama-2-7b-16k-gguf/general) | Q4_0 | 4.7 GB |
|
| 51 |
-
| [shaowenchen/chinese-llama-2-7b-16k-gguf:Q4_K](https://hub.docker.com/repository/docker/shaowenchen/chinese-llama-2-7b-16k-gguf/general) | Q4_K | 4.95 GB |
|
| 52 |
-
| [shaowenchen/chinese-llama-2-7b-16k-gguf:Q4_K_S](https://hub.docker.com/repository/docker/shaowenchen/chinese-llama-2-7b-16k-gguf/general) | Q4_K_S | 4.73 GB |
|
| 53 |
-
|
| 54 |
-
```
|
| 55 |
-
docker run --rm -p 8000:8000 shaowenchen/chinese-llama-2-7b-16k-gguf:Q2_K
|
| 56 |
-
```
|
| 57 |
-
|
| 58 |
-
并打开 http://localhost:8000/docs 查看 API 文档。
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
configuration.json
CHANGED
|
@@ -3,5 +3,8 @@
|
|
| 3 |
"task": "text-generation",
|
| 4 |
"model": {
|
| 5 |
"type": "llama2"
|
|
|
|
|
|
|
|
|
|
| 6 |
}
|
| 7 |
}
|
|
|
|
| 3 |
"task": "text-generation",
|
| 4 |
"model": {
|
| 5 |
"type": "llama2"
|
| 6 |
+
},
|
| 7 |
+
"pipeline": {
|
| 8 |
+
"type": "chinese-alpaca-2-7b-16k-text-generation-pipe"
|
| 9 |
}
|
| 10 |
}
|