Update README.md
Browse files
README.md
CHANGED
@@ -10,7 +10,12 @@ widget:
|
|
10 |
|
11 |
## MiniChat-1.5-3B
|
12 |
|
13 |
-
📑 [arXiv](https://arxiv.org/abs/2311.07052) | 👻 [GitHub](https://github.com/GeneZC/MiniMA) | 🤗 [HuggingFace-MiniMA](https://huggingface.co/GeneZC/MiniMA-3B) | 🤗 [HuggingFace-MiniChat](https://huggingface.co/GeneZC/MiniChat-3B) | 🤖 [ModelScope-MiniMA](https://modelscope.cn/models/GeneZC/MiniMA-3B) | 🤖 [ModelScope-MiniChat](https://modelscope.cn/models/GeneZC/MiniChat-3B)
|
|
|
|
|
|
|
|
|
|
|
14 |
|
15 |
❗ Must comply with LICENSE of LLaMA2 since it is derived from LLaMA2.
|
16 |
|
@@ -18,8 +23,6 @@ A language model distilled and finetuned from an adapted version of LLaMA2-7B fo
|
|
18 |
|
19 |
Outperforming a wide range of 3B competitors in GPT4 evaluation and even competing with several 7B chat models.
|
20 |
|
21 |
-
**Updates from MiniChat-3B**: 1) better data mixture; 2) use of [NEFTune](https://arxiv.org/abs/2310.05914); 3) use of [DPO](https://arxiv.org/abs/2305.18290)
|
22 |
-
|
23 |
<img src="./teaser_b.jpg" alt="teaser_b" width="687" />
|
24 |
|
25 |
The following is an example code snippet to use MiniChat-3B:
|
|
|
10 |
|
11 |
## MiniChat-1.5-3B
|
12 |
|
13 |
+
📑 [arXiv](https://arxiv.org/abs/2311.07052) | 👻 [GitHub](https://github.com/GeneZC/MiniMA) | 🤗 [HuggingFace-MiniMA](https://huggingface.co/GeneZC/MiniMA-3B) | 🤗 [HuggingFace-MiniChat](https://huggingface.co/GeneZC/MiniChat-3B) | 🤗 [HuggingFace-MiniChat-1.5](https://huggingface.co/GeneZC/MiniChat-1.5-3B) | 🤖 [ModelScope-MiniMA](https://modelscope.cn/models/GeneZC/MiniMA-3B) | 🤖 [ModelScope-MiniChat](https://modelscope.cn/models/GeneZC/MiniChat-3B)
|
14 |
+
|
15 |
+
🆕 **Updates from MiniChat-3B**:
|
16 |
+
- better data mixture;
|
17 |
+
- use of [NEFTune](https://arxiv.org/abs/2310.05914);
|
18 |
+
- use of [DPO](https://arxiv.org/abs/2305.18290).
|
19 |
|
20 |
❗ Must comply with LICENSE of LLaMA2 since it is derived from LLaMA2.
|
21 |
|
|
|
23 |
|
24 |
Outperforming a wide range of 3B competitors in GPT4 evaluation and even competing with several 7B chat models.
|
25 |
|
|
|
|
|
26 |
<img src="./teaser_b.jpg" alt="teaser_b" width="687" />
|
27 |
|
28 |
The following is an example code snippet to use MiniChat-3B:
|