How to use cometadata/funding-extraction-qwen3.5-9B-non-thinking-artifact-data-mix-grpo-mixed-reward with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3.5-9B") model = PeftModel.from_pretrained(base_model, "cometadata/funding-extraction-qwen3.5-9B-non-thinking-artifact-data-mix-grpo-mixed-reward")
https://huggingface.co/cometadata/funding-extraction-qwen3.5-9B-non-thinking-artifact-data-mix-grpo-mixed-reward/resolve/main/vocab.json
hf download hf://cometadata/funding-extraction-qwen3.5-9B-non-thinking-artifact-data-mix-grpo-mixed-reward/vocab.json
curl -L -o vocab.json https://huggingface.co/cometadata/funding-extraction-qwen3.5-9B-non-thinking-artifact-data-mix-grpo-mixed-reward/resolve/main/vocab.json
