RichardEllis/qwen3.5-4b-reduction-coldstart
Add files using upload-large-folder tool
Add files using upload-large-folder tool
Update GRPO checkpoint upload status (10/10)
Add files using upload-large-folder tool
Add files using upload-large-folder tool
Update GRPO checkpoint upload status (9/10)
Add files using upload-large-folder tool
Add files using upload-large-folder tool
Update GRPO checkpoint upload status (8/10)
Add files using upload-large-folder tool
Add files using upload-large-folder tool
Update GRPO checkpoint upload status (7/10)
Add files using upload-large-folder tool
Add files using upload-large-folder tool
Update GRPO checkpoint upload status (6/10)
Add files using upload-large-folder tool
Add files using upload-large-folder tool
Update GRPO checkpoint upload status (5/10)
Add files using upload-large-folder tool
Add files using upload-large-folder tool
Update GRPO checkpoint upload status (4/10)
Add files using upload-large-folder tool
Add files using upload-large-folder tool
Update GRPO checkpoint upload status (3/10)
Add files using upload-large-folder tool
Add files using upload-large-folder tool
Update GRPO checkpoint upload status (2/10)
Add files using upload-large-folder tool
Add files using upload-large-folder tool
Update GRPO checkpoint upload status (1/10)
Add files using upload-large-folder tool
Add files using upload-large-folder tool
Start GRPO checkpoint upload
cold-start SFT merged weights (4-teacher distillation, LoRA r64 merged)
Apache-2.0 (inherited from Qwen3.5-4B)
model card
initial commit
