Downloads · 30 days
100
0% of all-time downloads
adamo1139/Yi-34B-200K-rawrr1-LORA-DPO-experimental-r3
Yi-34B-200K-rawrr1-LORA-DPO-experimental-r3 is a text generation model from adamo1139. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
Another QLoRA DPO training of Yi-34B-200K. This time with sequence length 500, lorar 16 and lora alpha 32. I was able to squeeze that in using Unsloth, script I used is in this repo. It definitely has much stronger ef…
Downloads · 30 days
100
0% of all-time downloads
All-time downloads
36.3K
Public
Repo size
493 MB
Likes
1
Public
Click a slice to open those files.
.safetensors492 MB · 100%
From the Hugging Face model README
Another QLoRA DPO training of Yi-34B-200K. This time with sequence length 500, lora_r 16 and lora alpha 32. I was able to squeeze that in using Unsloth, script I used is in this repo. It definitely has much stronger effect than my previous one that was with lora_r 4, lora_alpha 8 and sequence length 200, but I am not sure if I didn't overcook it. Will try to train this on AEZAKMI v2 now.
Credits for mlabonne (I was using his Mistral fine-tuning script pieces for dataset preparation), Daniel Han and Michael Han (Unsloth AI team)