Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
language:
|
4 |
+
- zh
|
5 |
+
- en
|
6 |
+
library_name: transformers
|
7 |
+
pipeline_tag: text-generation
|
8 |
+
---
|
9 |
+
原始模型:https://huggingface.co/Neko-Institute-of-Science/pygmalion-7b
|
10 |
+
|
11 |
+
lora:https://huggingface.co/ziqingyang/chinese-alpaca-plus-lora-13b
|
12 |
+
|
13 |
+
将pygmalion-7b与chinese-alpaca-lora-13b进行合并,增强模型的中文能力,~~不过存在翻译腔~~
|
14 |
+
|
15 |
+
使用项目:
|
16 |
+
https://github.com/ymcui/Chinese-LLaMA-Alpaca
|
17 |
+
|
18 |
+
https://github.com/qwopqwop200/GPTQ-for-LLaMa
|
19 |
+
|
20 |
+
**兼容AutoGPTQ和GPTQ-for-LLaMa**
|
21 |
+
**若选择GPTQ-for-LLaMa加载,请设置 Wbits=4 groupsize=128 model_type=llama**
|
22 |
+
|
23 |
+
|
24 |
+
Text-generation-webui懒人包:
|
25 |
+
https://www.bilibili.com/read/cv23495183
|
26 |
+
|
27 |
+
---
|
28 |
+
|
29 |
+
Original model: https://huggingface.co/TheBloke/Wizard-Vicuna-13B-Uncensored-HF
|
30 |
+
|
31 |
+
lora:https://huggingface.co/ziqingyang/chinese-alpaca-plus-lora-13b
|
32 |
+
|
33 |
+
The pygmalion-7b model is combined with the chinese-alpaca-lora-13b model to enhance the model's Chinese language capabilities, ~~although there may be some translated tone~~.
|
34 |
+
|
35 |
+
Usage projects:
|
36 |
+
https://github.com/ymcui/Chinese-LLaMA-Alpaca
|
37 |
+
|
38 |
+
https://github.com/qwopqwop200/GPTQ-for-LLaMa
|
39 |
+
|
40 |
+
**Compatible with AutoGPTQ and GPTQ-for-LLaMa**
|
41 |
+
**If you choose to load GPTQ-for-LLaMa, please set Wbits=4 groupsize=128 model_type=llama**
|