AnthonyNwafor/gpt-oss-20b-ttrl-merged

This repository contains the merged model produced by semi-online test-time reinforcement learning on gpt-oss-20b for olympiad-style mathematics.

Training Summary

• Base model: danielhanchen/gpt-oss-20b
• Training method: semi-online TTRL with vLLM rollout collection and reward-filtered QLoRA updates
• CSV schema used: id, category, problem, answer, source
• Topics processed: Algebra, Number Theory
• Best recorded eval accuracy: not recorded
• Mean recorded rollout reward: 0.7031
• Model card generated at: 2026-04-05 13:02:06 UTC
• Template version: 2026-04-04

Artifact Details

• Artifact type: merged model
• Local merged directory: ttrl_artifacts/merged_model

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

repo_id = 'AnthonyNwafor/gpt-oss-20b-ttrl-merged'

tokenizer = AutoTokenizer.from_pretrained(repo_id, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(repo_id, trust_remote_code=True)

Notes

• Rollouts were collected with a local vLLM OpenAI-compatible server.
• Training data provenance should be tracked separately alongside the rollout JSONL files and summary CSV.
• If you publish benchmark numbers, keep held-out evaluation separate from any adaptation pool.