GaryZhou/MMR-RL-only

reinforcement-learning model by GaryZhou

Older snapshot: check the original source for current information.

From the publisher

Model card & documentation

Source preview

Read the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.

Merged model of Qwen3-8B GRPO RL checkpoints trained on AppWorld, produced by the S3 recipe: Maximal Marginal Relevance (MMR) checkpoint selection + steep softmax weighting + TIES sign-consensus merge, all in float32. AppWorld official eval stack (same code path as training validation), T=0.5, n=1, fp32 engine: Best single checkpoint (270/300): dev 0.6667 → +5 tasks over the best single checkpoint. Key ablation: pruning the bank to the two strongest members ({270, 300} equal weight) drops dev to 0.5439 (−12 tasks). The gain comes from near-zero-weight members participating in the TIES sign election — "wide bank + steep weights" are jointly necessary, not winner-take-all. ⚠️ Note: dev@1 (T=0.5, n=1) has a measured noise band of ±6/57 tasks between two identical-model runs; the +5-task margin is at the edge of this band and awaits…

GaryZhou/MMR-RL-only on Hugging Face A short preview, not the full document.

Read the full model card ↗ · Preview checked 2026-10-28T00:59:48.458Z

Inside the original model card — Document outline

Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.

Documentation belongs to its respective authors. Reported project/model license: apache-2.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.

Model overview

GaryZhou/MMR-RL-only is a reinforcement-learning model repository published by GaryZhou on Hugging Face. The source reports the transformers library.

This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.

Model facts

Task: reinforcement-learning
Library: transformers
Recent downloads (30 days): 0
Cumulative likes: 0
Hugging Face trending score: 0
Reported safetensors parameters: Not reported
Architecture: Not reported
License: apache-2.0
Access: Not gated by Hugging Face
Created: 2026-10-19T06:04:35.000Z
Last modified: 2026-10-19T06:39:40.000Z

Compatibility and lineage

Language coverage was not reported.

Reported base models: Qwen/Qwen3-8B

Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.

Use and evaluate

Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.

No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.

Model card and usage instructions

Model files and configuration

Community discussion