Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
datasets:
|
4 |
+
- timdettmers/openassistant-guanaco
|
5 |
+
pipeline_tag: conversational
|
6 |
+
base_model: internlm/internlm2-7b
|
7 |
+
---
|
8 |
+
|
9 |
+
<div align="center">
|
10 |
+
<img src="https://github.com/InternLM/lmdeploy/assets/36994684/0cf8d00f-e86b-40ba-9b54-dc8f1bc6c8d8" width="600"/>
|
11 |
+
|
12 |
+
|
13 |
+
[![Generic badge](https://img.shields.io/badge/GitHub-%20XTuner-black.svg)](https://github.com/InternLM/xtuner)
|
14 |
+
|
15 |
+
|
16 |
+
</div>
|
17 |
+
|
18 |
+
## Model
|
19 |
+
|
20 |
+
internlm2-7b-qlora-oasst1 is fine-tuned from [InternLM2-7B](https://huggingface.co/internlm/internlm2-7b) with [openassistant-guanaco](https://huggingface.co/datasets/timdettmers/openassistant-guanaco) dataset by [XTuner](https://github.com/InternLM/xtuner).
|
21 |
+
|
22 |
+
|
23 |
+
## Quickstart
|
24 |
+
|
25 |
+
### Usage with XTuner CLI
|
26 |
+
|
27 |
+
#### Installation
|
28 |
+
|
29 |
+
```shell
|
30 |
+
pip install xtuner
|
31 |
+
```
|
32 |
+
|
33 |
+
#### Chat
|
34 |
+
|
35 |
+
```shell
|
36 |
+
xtuner chat internlm/internlm2-7b --adapter xtuner/internlm2-7b-qlora-oasst1 --prompt-template internlm2_chat
|
37 |
+
```
|
38 |
+
|
39 |
+
#### Fine-tune
|
40 |
+
|
41 |
+
Use the following command to quickly reproduce the fine-tuning results.
|
42 |
+
|
43 |
+
```shell
|
44 |
+
xtuner train internlm2_7b_qlora_oasst1_e3
|
45 |
+
```
|