hbin0701/Qwen3-1.7B-rewind-sftv3-wait
text-generation model by hbin0701
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.
Qwen3-1.7B fine-tuned to use a single-token action while it thinks. Writing asks the environment to erase the last 4 sections of the reasoning, insert [rewound], and let the model continue from there (at most once per solution, never after ). This is the SFT start for RL. It was trained to give a small, fixed probability (P0 = 2.5%) at legal spots and 0 elsewhere, and was never shown a to copy. Deciding when to fire is left to RL. Code: hbin0701/sclm, branch rl/paired-rloo-stability-hb (rewind/sfttrain.py, launched by sftprior.sh). string). It sits in a spare embedding row. Its embedding was initialised to the mean of the embeddings of "Wait", "Alternatively" and "Hmm". Embeddings are tied, so this sets its output logit row too. 3 paragraphs, once the current section has at least 300 tokens. The count is causal: the section starts of a prefix are the section starts of the whole…
Read the full model card ↗ · Preview checked 2026-10-30T14:11:48.021Z
Inside the original model card — Document outline
- Qwen3-1.7B · SFT v3 ("prior mode", wait init)
- The tag and the environment
- Training data
- Loss (exact)
- Results
- Usage
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the model card
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
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
hbin0701/Qwen3-1.7B-rewind-sftv3-wait is a text-generation model repository published by hbin0701 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
- text-generation
- Library
- transformers
- Recent downloads (30 days)
- 0
- Cumulative likes
- 0
- Hugging Face trending score
- 0
- Reported safetensors parameters
- 1,720,574,976
- Architecture
- Qwen3ForCausalLM
- License
- apache-2.0
- Access
- Not gated by Hugging Face
- Created
- 2026-10-10T06:35:07.000Z
- Last modified
- 2026-10-10T06:35:49.000Z
Compatibility and lineage
Language coverage was not reported.
Reported base models: Qwen/Qwen3-1.7B
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 2026-10-10T06:41:01.047Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.