Update README.md
Browse files
README.md
CHANGED
|
@@ -7,12 +7,14 @@ pipeline_tag: summarization
|
|
| 7 |
<b style="font-size: 40px;">SummLlama3-8B</b>
|
| 8 |
</div>
|
| 9 |
|
| 10 |
-
Are you looking for a summarizer that
|
| 11 |
|
| 12 |
Our **SummLlama3-8B** could be exactly what you need!
|
| 13 |
|
| 14 |
SummLlama3 is initialized from Llama3-8B-Instruct, with additional training using Direct Preference Optimization (DPO) based on human-like summarization feedback.
|
| 15 |
|
|
|
|
|
|
|
| 16 |
Please refer to [our paper](link) to catch up how to exploit LLM-generated feedback in the context of text summarization.
|
| 17 |
|
| 18 |
We also released a larger model, **SummLlama3-70B**. Please go to the [Huggingface link](https://huggingface.co/DISLab/SummLlama3-70B) for this model.
|
|
|
|
| 7 |
<b style="font-size: 40px;">SummLlama3-8B</b>
|
| 8 |
</div>
|
| 9 |
|
| 10 |
+
Are you looking for a summarizer that can generate more **human-preferred summaries**?
|
| 11 |
|
| 12 |
Our **SummLlama3-8B** could be exactly what you need!
|
| 13 |
|
| 14 |
SummLlama3 is initialized from Llama3-8B-Instruct, with additional training using Direct Preference Optimization (DPO) based on human-like summarization feedback.
|
| 15 |
|
| 16 |
+
It outperforms the nearly 10x larger Llama3-70B-Instruct while offering much faster inference speed.
|
| 17 |
+
|
| 18 |
Please refer to [our paper](link) to catch up how to exploit LLM-generated feedback in the context of text summarization.
|
| 19 |
|
| 20 |
We also released a larger model, **SummLlama3-70B**. Please go to the [Huggingface link](https://huggingface.co/DISLab/SummLlama3-70B) for this model.
|