sagnikM/qwen_qwen_step75_prior

HiLL Qwen2.5-7B prior — step 75

The question-only hint generator converted from the step-75 FSDP checkpoint of the HiLL Qwen2.5-7B/OpenThoughts run.

from transformers import AutoModelForCausalLM, AutoTokenizer

repo_id = "sagnikM/qwen_qwen_step75_prior"
model = AutoModelForCausalLM.from_pretrained(repo_id, torch_dtype="auto")
tokenizer = AutoTokenizer.from_pretrained(repo_id)

Only model, configuration, and tokenizer artifacts are uploaded; optimizer and trainer state remain in the original VERL checkpoint.