You need to agree to share your Hugging Face information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Log in or Sign Up to review the conditions and access this model content.

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

t090-C8s-c01-uinst: head C8s x8, 126 tasks (t-090, idea 767)

Render: UINST: one user message, content = system_prompt + '\n\n' + prompt (instruction FIRST, then the problem), apply_chat_template([user], add_generation_prompt=True), no system message, no enable_thinking kwarg (gen.py UONLY=1 UINST=1, line 62). Sampling: vLLM 0.32.0, temperature 1.0, top_k 20, top_p 0.95, max_tokens 8192, n 8. Graded by gen.py (math-verify; outcome correct|wrong|unresolved; unresolved = not EOS or no canonical think + exactly one boxed). t090-C8s-c01-uinst_all.jsonl: one line per task: task, prompt (ids), prompt_text, tri, k, n, rollouts[{tokens, stop eos|max_tokens, outcome, text}]. text = decode(tokens), ends with <|im_end|> when stop=eos. rows_all.tsv: task n k cut tokmed (upper median).

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support