Downloads · 30 days
0
gpt-oss-20b-ttrl-adapter
AnthonyNwafor/gpt-oss-20b-ttrl-adapter
gpt-oss-20b-ttrl-adapter is a reinforcement learning model from AnthonyNwafor. Use it for the reinforcement learning task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as other.
This repository contains the adapter produced by semi-online test-time reinforcement learning on gpt-oss-20b for olympiad-style mathematics.
Access
Public
Updated Apr 5, 2026
Repo size
91.8 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors63.7 MB · 69%
At a glance
- Task
- Reinforcement Learning
- Library
- transformers
- License
- other
- Access
- Public
- Created
- Apr 5, 2026
- Updated
- Apr 5, 2026
- SHA
- 3b344c4a
Base models
Model card
From the Hugging Face model README
AnthonyNwafor/gpt-oss-20b-ttrl-adapter
This repository contains the adapter 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: LoRA/QLoRA adapter
- Latest adapter path:
ttrl_artifacts/adapters/algebra_batch_000
Usage
from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer
base_model_name = 'danielhanchen/gpt-oss-20b'
adapter_repo_id = 'AnthonyNwafor/gpt-oss-20b-ttrl-adapter'
tokenizer = AutoTokenizer.from_pretrained(base_model_name, trust_remote_code=True)
base_model = AutoModelForCausalLM.from_pretrained(base_model_name, trust_remote_code=True)
model = PeftModel.from_pretrained(base_model, adapter_repo_id)
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.
- Task
- Reinforcement Learning
- Library
- transformers
- License
- other
- Created
- Apr 5, 2026
- Updated
- Apr 5, 2026