How to use Weisly/Qwen3-8b-grpo with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Weisly/Qwen3-8b-grpo", device_map="auto")
https://huggingface.co/Weisly/Qwen3-8b-grpo/resolve/main/checkpoint-800/vocab.json
hf download hf://Weisly/Qwen3-8b-grpo/checkpoint-800/vocab.json
curl -L -o vocab.json https://huggingface.co/Weisly/Qwen3-8b-grpo/resolve/main/checkpoint-800/vocab.json
