sandeep123/grpo-qwen3-4b-nonthinking-likelihood-2048-20260918
text-generation model by sandeep123
Older snapshot: check the original source for current information.
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
GRPO with a detached correct-response likelihood-rank reward; exact equation and provenance are recorded in baseline metadata. Training explicitly renders enablethinking=False, recorded as thinkingmode: false in the scientific contract. The pinned tokenizer and chat template remain unchanged. Use the same explicit keyword at inference, particularly for Qwen3-1.7B, whose default template enables thinking. Every checkpoint in this repository requires explicit nonthinking provenance. This public repository retains every published optimizer-update adapter, including update zero (the initial, untrained adapter). Training is planned for 4 epochs on the same 2,048-question training split as the earlier STRIDE runs. The global prompt batch is 64 questions with eight rollouts each (512 responses per update), giving 32 updates per epoch and 128 planned updates. Prompt plus response context is capped at 8,192 tokens; the random seed is 42. Completion is reported by actual entries in checkpointindex.json; planned epochs do not imply that training has finished. No evaluation or…
Read the full model card ↗ · Preview checked 2026-10-29T16:03:31.934Z
Inside the original model card — Document outline
- Qwen/Qwen3-4B-Instruct-2507: grpolikelihood, coefficient=0.25
- Reload a particular adapter
- Inference versus training resume
- Verified server storage policy
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Documentation belongs to its respective authors. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
sandeep123/grpo-qwen3-4b-nonthinking-likelihood-2048-20260918 is a text-generation model repository published by sandeep123 on Hugging Face. The source reports the peft library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- text-generation
- Library
- peft
- Recent downloads (30 days)
- 0
- Cumulative likes
- 0
- Hugging Face trending score
- 0
- Reported safetensors parameters
- Not reported
- Architecture
- Not reported
- License
- Not reported — check the model card
- Access
- Not gated by Hugging Face
- Created
- 2026-09-18T06:08:35.000Z
- Last modified
- 2026-09-18T06:08:37.000Z
Compatibility and lineage
Language coverage was not reported.
Reported base models: Qwen/Qwen3-4B-Instruct-2507
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.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-09-18T06:35:09.247Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.