Update README.md
Browse files
README.md
CHANGED
|
@@ -6,17 +6,34 @@ tags:
|
|
| 6 |
- unsloth
|
| 7 |
- llama
|
| 8 |
- trl
|
| 9 |
-
license: apache-2.0
|
| 10 |
language:
|
| 11 |
-
-
|
| 12 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13 |
|
| 14 |
# Uploaded model
|
| 15 |
|
| 16 |
- **Developed by:** OsakanaTeishoku
|
| 17 |
-
- **License:**
|
| 18 |
- **Finetuned from model :** llm-jp/llm-jp-3-13b
|
| 19 |
|
| 20 |
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
|
| 21 |
|
| 22 |
-
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
|
|
|
| 6 |
- unsloth
|
| 7 |
- llama
|
| 8 |
- trl
|
|
|
|
| 9 |
language:
|
| 10 |
+
- ja
|
| 11 |
---
|
| 12 |
+
# はじめに
|
| 13 |
+
これは，東京大学松尾・岩澤研究室のLLM講座2024のコンペティションで提出するためのモデルです．
|
| 14 |
+
llm-jp/llm-jp-3-13bに，QLoRAによるSFTを施して，LoRAアダプタのみをこちらにアップしています．
|
| 15 |
+
chat templateは，weblab-GENIAC/Tanuki-8B-dpo-v1.0のものと同一のものを使用しています．
|
| 16 |
+
|
| 17 |
+
# 推論方法
|
| 18 |
+
提供された環境で，以下のように推論します．L4 GPU×1のインスタンスで，vLLMを用いて推論します．
|
| 19 |
+
Jupyter Notebookで，一かたまりごとに一つのセルになっています．順番に実行してください．
|
| 20 |
+
```python
|
| 21 |
+
a
|
| 22 |
+
```
|
| 23 |
+
|
| 24 |
+
|
| 25 |
+
|
| 26 |
+
|
| 27 |
+
|
| 28 |
+
|
| 29 |
+
|
| 30 |
|
| 31 |
# Uploaded model
|
| 32 |
|
| 33 |
- **Developed by:** OsakanaTeishoku
|
| 34 |
+
- **License:** cc-by-nc-sa-4.0
|
| 35 |
- **Finetuned from model :** llm-jp/llm-jp-3-13b
|
| 36 |
|
| 37 |
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
|
| 38 |
|
| 39 |
+
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|