Instructions to use HumorR1/policy-e2a-grpo-no-thinking with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use HumorR1/policy-e2a-grpo-no-thinking with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("/home/ubuntu/code/humor-r1/checkpoints/qwen3vl-2b-sft-instruct-nothink-merged") model = PeftModel.from_pretrained(base_model, "HumorR1/policy-e2a-grpo-no-thinking") - Notebooks
- Google Colab
- Kaggle
File size: 133 Bytes
3c6d6e2 | 1 2 3 4 | version https://git-lfs.github.com/spec/v1
oid sha256:79cb3c783570f1b8fe73b9ed530ae50cae9ce4b6344c0b5edefc50478847eaa4
size 11422817
|