Update README.md
Browse files
README.md
CHANGED
|
@@ -28,16 +28,6 @@ This specific repository contains the **10B parameter model**, refined with **Di
|
|
| 28 |
|
| 29 |
**Note:** This set of model parameters is specifically formatted for the 🤗 Transformers library! If you want to use Evolla with our [original custom repository](https://github.com/westlake-repl/Evolla), please check [Evolla-10B](https://huggingface.co/westlake-repl/Evolla-10B) or [Evolla-10B-DPO](https://huggingface.co/westlake-repl/Evolla-10B-DPO).
|
| 30 |
|
| 31 |
-
## Comparative Analysis
|
| 32 |
-
|
| 33 |
-
In our paper, we conducted a comparative analysis against two state-of-the-art general-purpose language models: `Deepseek-v3` and `gpt-4o-2024-11-20`. Evolla demonstrates expert-level insights and significantly outperforms general LLMs in protein functional inference.
|
| 34 |
-
|
| 35 |
-
| Model | Mean GPT score (± 95% confidence interval) |
|
| 36 |
-
| :--- | :--- |
|
| 37 |
-
| **Evolla** | **74.10 ± 0.81** |
|
| 38 |
-
| Deepseek-v3 | 40.49 ± 0.56 |
|
| 39 |
-
| gpt-4o-2024-11-20 | 37.07 ± 0.54 |
|
| 40 |
-
|
| 41 |
## Usage with 🤗 Transformers
|
| 42 |
|
| 43 |
You can load and use `Evolla-10B-DPO-hf` directly using the standard Hugging Face API. Please ensure that your `aa_seq` and `foldseek` sequences have the exact same length.
|
|
|
|
| 28 |
|
| 29 |
**Note:** This set of model parameters is specifically formatted for the 🤗 Transformers library! If you want to use Evolla with our [original custom repository](https://github.com/westlake-repl/Evolla), please check [Evolla-10B](https://huggingface.co/westlake-repl/Evolla-10B) or [Evolla-10B-DPO](https://huggingface.co/westlake-repl/Evolla-10B-DPO).
|
| 30 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 31 |
## Usage with 🤗 Transformers
|
| 32 |
|
| 33 |
You can load and use `Evolla-10B-DPO-hf` directly using the standard Hugging Face API. Please ensure that your `aa_seq` and `foldseek` sequences have the exact same length.
|