Fix: bump bitsandbytes to 0.45.3 for CUDA 12.x support on Kaggle T4 6bf2fbb
shank commited on
Commit History
Optimize for Kaggle P100: float16, batch=1, grad_accum=8, num_gen=4, max_completion=256, lora_r=8 73f957d
shank commited on
Fix GRPOConfig: rename max_new_tokens to max_completion_length for trl==0.14.0 8b16369
shank commited on
Update: Added testing a5c67b3
shank commited on
Align gradio version with Hugging Face Space builder2 633a3b7
shank commited on
Add dockerignore to reduce Space build context c945597
shank commited on
Stabilize Space runtime: pin ML deps and disable runtime package drift 663b8db
shank commited on
Pin torch to cu121 build + use model.device instead of hardcoded cuda string 8f291e0
shank commited on
Replace unsloth with bitsandbytes+peft: fixes CUDA driver incompatibility on HF A100 c325ad7
shank commited on
Fix Gradio 4.x every= deprecation: use gr.Timer for auto-refresh 5eea2dd
shank commited on
Reduce training to 500 steps with tightened curriculum for A10G budget ba8df98
shank commited on
Add Gradio training monitor and fix subprocess python path b37b2eb
shank commited on
Fix eval device selection with CUDA-safe fallback dc8001b
shank commited on
Add interactive Gradio demo at /demo in env Space 4bac574
shank commited on
Optimize for A100 80GB: 8 generations, batch 4, lr 2e-5, dense logging 2b1fbf3
shank commited on
Restore full 1000-step training with original curriculum 1128de1
shank commited on
Reduce training to 500 steps with tightened curriculum for A10G budget 3152fa9
shank commited on
"Update: Minor fixes" 755a07d
shank commited on
Add Gradio training monitor and fix subprocess python path b92ad01
shank commited on
Curated the bugs dataset 85f14d3
PulipatiPranav commited on
Resolved README Merge conflicts a693c08
PulipatiPranav commited on
Update: Started making changes for the hackathon a55c81d
shank commited on
Updated README.md a849e43
Pranav Pulipati commited on
Update: Refined and validated values 6cca39d
shank commited on
Update: Even more Final README.md update 5c507c3
shank commited on
Update: Final README.md update 3548cd0
shank commited on
Update: Final README.md update 4057375
shank commited on
Fix: Changed environment variables and added validator e93446d
shank commited on
Fix: Final submission cleanup, unified identity and integrity markers 8807d25
shank commited on
Update: Made refinements to the project 159a5fa
shank commited on
Fix: Revise README for improved clarity and detail 1c8aca2
Shashaank commited on
Update: README e4f09cc
Shashaank commited on
Fix: Changed scores range 0769caa
shank commited on
Fix: Changed dependencies ea7105c
shank commited on
Fix: Change in gitignore cd3a400
shank commited on
Fix: Remove gitignore from commits 62a3a90
shank commited on
Fix: Formatted the output 0181886
shank commited on
Update: Dockerfile and inference.py 212d2d9
shank commited on
Fix: precaution to prevent infinite loop cd968e7
shank commited on
Fix: Fixed exception handling in inference.py 2a482a5
shank commited on
docs: updated the readme and added a license a2ff803
shank commited on
docs: updated the readme and added a license 22cb7e7
shank commited on
fix: score floor for medium grader, add root and tasks endpoints b658e10
shank commited on
Cleaner code and logic improvement ee08016
shank commited on
docs: final professional polish and code sanitization 9940e16
shank commited on
Add server/app.py entry point for OpenEnv validation ade347f
shank commited on
chore: include lockfile for reproducible deployment 8b39a8b
shank commited on
Update pyproject.toml for OpenEnv validation ca23d0f
shank commited on
Add pyproject.toml for OpenEnv validation d765986
shank commited on
made changes to server.py f2ee2fc
shank commited on