File size: 946 Bytes
515b3de 00cfded 515b3de cc29995 eef6a56 06128af cc29995 df1d4d4 b34565e 30a4b45 cc29995 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 |
---
license: cc-by-2.0
---
Finetune of miqu-70b-sf dequant of miqudev's leak of Mistral-70B (allegedly an early mistral medium). My diffs are available under CC-0 (That is the Senku-70B repo, full includes the merge), this is a merge with the leaked model, you can use the other repository to save bandwidth.
EQ-Bench: 84.89
GSM8k: 77.18 (71.04 when using ChatML)
Hellaswag: 87.67
Edit: Upon further testing a score of 85.09 was achieved using ChatML instead of Mistral's prompt.
I recommend using the ChatML format instead, I will run more benchmarks. This also fixes the bug with Miqu dequant failing to provide a stop.
<|im_start|>system
Provide some context and/or instructions to the model.
<|im_end|>
<|im_start|>user
The user’s message goes here
<|im_end|>
<|im_start|>assistant <|im_end|>
Credit to https://twitter.com/hu_yifei for providing GSM & Hellaswag. It is the first open weight model to dethrone GPT-4 on EQ bench, |