Views
No views yet
rl_finetune_grpo.py) on StackOverflow-style SQL, continuing from abharadwaj123/llama3-sql2plan.model.safetensors), tokenizer, config. Optimizer state was omitted to save space.1from transformers import AutoModelForCausalLM, AutoTokenizer
2m = AutoModelForCausalLM.from_pretrained("REPO_ID", torch_dtype="auto", device_map="auto")
3tok = AutoTokenizer.from_pretrained("REPO_ID")