Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
Asap7772
/
Qwen3-4B-second-stage-DPO-lr-1e-6-beta-0.05-loss-sigmoid-rpo-1.0-ckpt-135
like
0
Safetensors
qwen3
trl
dpo
rlhf
alignment
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
main
Qwen3-4B-second-stage-DPO-lr-1e-6-beta-0.05-loss-sigmoid-rpo-1.0-ckpt-135
/
zero_to_fp32.py
Commit History
Upload checkpoint from checkpoint-135
90856ea
verified
Asap7772
commited on
Sep 16