coyude commited on
Commit
85d9326
1 Parent(s): 8b9f377

Create README.md

Browse files
Files changed (1) hide show
  1. README.md +41 -0
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**