Update README.md
Browse files
README.md
CHANGED
|
@@ -175,10 +175,10 @@ model-index:
|
|
| 175 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 176 |
should probably proofread and complete it, then remove this comment. -->
|
| 177 |
|
| 178 |
-
<img src="https://alt-web.xyz/images/rainbow.png" alt="Rainbow Solutions" width="800" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
|
| 179 |
-
|
| 180 |
<h1 style='text-align: center'>Devi 7B</h1>
|
| 181 |
-
<h2 style='text-align: center'>Fork of Zephyr 7B β</h2>
|
|
|
|
|
|
|
| 182 |
|
| 183 |
Zephyr is a series of language models that are trained to act as helpful assistants. Zephyr-7B-β is the second model in the series, and is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) that was trained on on a mix of publicly available, synthetic datasets using [Direct Preference Optimization (DPO)](https://arxiv.org/abs/2305.18290). We found that removing the in-built alignment of these datasets boosted performance on [MT Bench](https://huggingface.co/spaces/lmsys/mt-bench) and made the model more helpful. However, this means that model is likely to generate problematic text when prompted to do so. You can find more details in the [technical report](https://arxiv.org/abs/2310.16944).
|
| 184 |
|
|
|
|
| 175 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 176 |
should probably proofread and complete it, then remove this comment. -->
|
| 177 |
|
|
|
|
|
|
|
| 178 |
<h1 style='text-align: center'>Devi 7B</h1>
|
| 179 |
+
<h2 style='text-align: center'>Fork of Zephyr 7B β</h2>
|
| 180 |
+
<h2 style='text-align: center '><em>All thanks to HuggingFaceH4 for their work!</em> </h2>
|
| 181 |
+
<img src="https://alt-web.xyz/images/rainbow.png" alt="Rainbow Solutions" width="800" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
|
| 182 |
|
| 183 |
Zephyr is a series of language models that are trained to act as helpful assistants. Zephyr-7B-β is the second model in the series, and is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) that was trained on on a mix of publicly available, synthetic datasets using [Direct Preference Optimization (DPO)](https://arxiv.org/abs/2305.18290). We found that removing the in-built alignment of these datasets boosted performance on [MT Bench](https://huggingface.co/spaces/lmsys/mt-bench) and made the model more helpful. However, this means that model is likely to generate problematic text when prompted to do so. You can find more details in the [technical report](https://arxiv.org/abs/2310.16944).
|
| 184 |
|