xDAN-L1-Chat-RL-v1 / README.md
xDAN2099's picture
Update README.md
e7d9d01
|
raw
history blame
3.02 kB
metadata
license: cc-by-4.0
datasets:
  - Open-Orca/OpenOrca
  - Intel/orca_dpo_pairs
language:
  - en
tags:
  - xDAN-AI
  - OpenOrca
  - DPO
  - Self-Think

xDAN-AI • > DiscordTwitterHuggingface

image/png

########## First turn ##########

model turn score
gpt-4 1 8.95625
xDAN-L1-Chat-RL-v1 1 8.87500
claude-v1 1 8.15000
gpt-3.5-turbo 1 8.07500
claude-instant-v1 1 7.80000
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
claude-instant-v1 2 8.012658
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.