Downloads · 30 days
0
tinker-rl-bench-kl_track_Qwen3-8B_s42
arvindcr4/tinker-rl-bench-kl_track_Qwen3-8B_s42
tinker-rl-bench-kl_track_Qwen3-8B_s42 is a reinforcement learning model from arvindcr4. Use it for the reinforcement learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
Modal H100 GPU experiment from TinkerRL-Bench world-class suite.
Access
Public
Updated Apr 19, 2026
Repo size
—
Likes
0
Public
Repo makeup
Click a slice to open those files.
Other1.5 KB · 47%
At a glance
- Task
- Reinforcement Learning
- License
- mit
- Access
- Public
- Created
- Apr 19, 2026
- Updated
- Apr 19, 2026
- SHA
- 8f3b5b5f
Base models
Datasets
Model card
From the Hugging Face model README
kl_track_Qwen3-8B_s42
Modal H100 GPU experiment from TinkerRL-Bench world-class suite.
Results
{
"experiment": "kl_track_Qwen3-8B_s42",
"model": "Qwen/Qwen3-8B",
"seed": 42,
"steps": 30,
"final_kl": 60.75,
"final_entropy": 0.7421875,
"max_kl": 60.75,
"platform": "modal_h100"
}
Citation
@misc{tinker-rl-bench-2026,
title={TinkerRL-Bench: A Unified Benchmark for RL Post-Training},
author={Arvind C R and Sandhya Jeyaraj and Madhu Kumara L and Mohammad Rafi and Dhruva N Murthy and Arumugam K},
year={2026},
url={https://github.com/arvindcr4/tinker-rl-lab}
}
- Task
- Reinforcement Learning
- License
- mit
- Created
- Apr 19, 2026
- Updated
- Apr 19, 2026