Text Generation
PEFT
Safetensors
lora
grpo
zero-rl
math
reward-design
paper-replication
recipe
while-ai
conversational
Instructions to use while-ai/paper-zero-rl-format-reward-4b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use while-ai/paper-zero-rl-format-reward-4b with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3.5-4B-Base") model = PeftModel.from_pretrained(base_model, "while-ai/paper-zero-rl-format-reward-4b") - Notebooks
- Google Colab
- Kaggle
Commit History
-
backfill: whileai-recipe-runs/zero-rl-recipe-s17-2026-09-21 -> recipe-seed17/
Verified signaturedf9530d -
backfill: whileai-recipe-runs/zero-rl-baseline-2026-09-18 -> baseline/
Verified signature0ec79ff -
backfill: whileai-recipe-runs/zero-rl-recipe-2026-09-18 -> root
Verified signature2eda7ef -
backfill: whileai-recipe-runs/zero-rl-baseline-s19-2026-09-21 -> baseline-seed19/
Verified signature56b9509 -
backfill: whileai-recipe-runs/zero-rl-baseline-s18-2026-09-21 -> baseline-seed18/
Verified signature046e1f3 -
backfill: whileai-recipe-runs/zero-rl-baseline-s17-2026-09-21 -> baseline-seed17/
Verified signature456f854 -
card
Verified signature3e212c5 -
backfill: whileai-recipe-runs/zero-rl-recipe-s19-2026-09-21 -> recipe-seed19/
Verified signatureea7bbfe -
backfill: whileai-recipe-runs/zero-rl-recipe-s18-2026-09-21 -> recipe-seed18/
Verified signature8c3d71d -
backfill: whileai-recipe-runs/zero-rl-recipe-s17-2026-09-21 -> root
Verified signature4f98ace -
initial commit
Verified signatureb5f6998