liangzhidanta/Qwen3-8B-CC-SFT-v2-2e
text-generation model by liangzhidanta
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.
English | 简体中文 Qwen3-8B-CC-SFT-v2-2e is the second-epoch compact-aware continued-SFT checkpoint, trained one additional epoch on the same compact-focused recipe as Qwen3-8B-CC-SFT-v2. It is the best-performing checkpoint of this SFT stage on the canonical303 coding-agent benchmark. canonical303 Pass@1: 54.79% (166/303) — 4090 run at T=0.4 (temperature selected on an independent dev set; see Temperature Selection). Wilson 95% CI: [49.16%, 60.29%]. 303/303 valid environments, 0 infrastructure failures. vs the published v2 (1-epoch) checkpoint, paired on identical 303 tasks (same 4090 harness family): For reference, the same v2-1e checkpoint at T=0.5 solved 159/303 (52.48%, paired p = 0.18 vs its T=0.3 run) — v2-2e @ T=0.4 and v2-1e @ T=0.5 are not statistically separable (p = 0.55), but v2-2e @ T=0.4 is the only configuration with a significant paired gain over the published v2 result. Dataset: liangzhidanta/claude-code-glm53-swesmith-compact-trajectories This checkpoint is the second epoch of the COMPACTFOCUSED recipe over the deployment-aligned (≤40960-token) subset of…
Read the full model card ↗ · Preview checked 2026-09-29T07:56:12.488Z
Inside the original model card — Document outline
- Qwen3-8B-CC-SFT-v2-2e
- Key Result
- Training Dataset and Recipe
- Training Details
- Training curve (both epochs, 734 optimizer steps)
- Temperature Selection
- Evaluation Protocol
- Model Lineage
- Usage
- Limitations
- Citation
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
liangzhidanta/Qwen3-8B-CC-SFT-v2-2e is a text-generation model repository published by liangzhidanta 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
- Not reported
- Architecture
- Not reported
- License
- apache-2.0
- Access
- Not gated by Hugging Face
- Created
- 2026-09-29T06:00:22.000Z
- Last modified
- 2026-09-29T06:03:30.000Z
Compatibility and lineage
Language coverage was not reported.
Reported base models: liangzhidanta/Qwen3-8B-CC-SFT-v2
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 2026-09-29T06:38:10.429Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.
Related models
trl-internal-testing/tiny-Qwen2ForCausalLM-2.5