---
license: cc-by-4.0
datasets:
- Open-Orca/OpenOrca
- Intel/orca_dpo_pairs
language:
- en
tags:
- xDAN-AI
- OpenOrca
- DPO
- Self-Think
---

<div style="display: flex; justify-content: center; align-items: center">
  <img src="https://cdn-uploads.huggingface.co/production/uploads/643197ac288c9775673a01e9/tVAcwKkIH5vkfzqgqHeHi.png" style="width: 45%;">
</div
>




## The first 7b model achieving an 8.8 on MT-Bench which is performance at Humanalities, Coding and Writing.
<p
 align="center"
  <a href="The TOP1 MT-Bench Model">xDAN-AI</a> •
>
  <a href="https://discord.gg/7NrMX5AK">Discord</a> •
  <a href="https://twitter.com/shootime007">Twitter</a> •
  <a href="https://huggingface.co/xDAN-AI">Huggingface</a>
</p>


![image/png](https://cdn-uploads.huggingface.co/production/uploads/643197ac288c9775673a01e9/QANDZApzpTHM6sBsjmdew.png)




########## First turn ##########
| model              | turn | score    |
|--------------------|------|----------|
| gpt-4              | 1    | 8.95625  |
| xDAN-L2-Chat-RL-v2 | 1    | 8.88750  |
| xDAN-L1-Chat-RL-v1 | 1    | 8.87500  |
| claude-v1          | 1    | 8.15000  |
| gpt-3.5-turbo      | 1    | 8.07500  |
| vicuna-33b-v1.3    | 1    | 7.45625  |
| wizardlm-30b       | 1    | 7.13125  |
| oasst-sft-7-llama-30b | 1 | 7.10625  |
| Llama-2-70b-chat   | 1    | 6.98750  |

########## Second turn ##########
| model              | turn | score     |
|--------------------|------|-----------|
| gpt-4              | 2    | 9.025000  |
| xDAN-L1-Chat-RL-v1 | 2   | 7.825000  |
| gpt-3.5-turbo      | 2    | 7.812500  |
| claude-v1          | 2    | 7.650000  |
| wizardlm-30b       | 2    | 6.887500  |
| vicuna-33b-v1.3    | 2    | 6.787500  |
| Llama-2-70b-chat   | 2    | 6.725000  |


########## Average turn##########
| model              | score     |
|--------------------|-----------|
| gpt-4              | 8.990625  |
| xDAN-L1-Chat-RL-v1 | 8.350000  |
| gpt-3.5-turbo      | 7.943750  |
| claude-instant-v1  | 7.905660  |
| claude-v1          | 7.900000  |
| vicuna-33b-v1.3    | 7.121875  |
| wizardlm-30b       | 7.009375  |
| Llama-2-70b-chat   | 6.856250  |



Prompt Template(Alpaca)
### Instruction:
{instruction}
### Response:


## Created By xDAN-AI at 2023-12-15
## Check: https://www.xdan.ai
 

Disclaimer
We employ data compliance checking algorithms during the training of our language model to strive for the highest degree of compliance. However, given the intricate nature of data and the vast array of potential usage scenarios for the model, we cannot assure that it will always generate correct and reasonable outputs. Users should be cognizant of the risk of the model producing problematic outputs. Our organization will not bear responsibility for any risks or issues stemming from misuse, misguidance, illegal use, and related misinformation, as well as any consequent data security concerns.

About xDAN-AI xDAN-AI is a top lead high-performance model factory. For detailed information and further insights into our cutting-edge technology and offerings, please visit our website: www.xdan.ai.