sthanika-ai/Sieve-27B-v2
text-classification model by sthanika-ai
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.
Sieve-27B-v2 is a decision model from the Sieve family. You give it a piece of text or JSON (the state) and typed questions, and it returns a calibrated probability for every option of every question. It reads the state once, scores the options directly, and never generates text. It is a full fine-tune of Qwen/Qwen3.8-27B (revision 1d4bf0f2) with a pointer head, and it stores one calibration temperature per question category. The code is at github.com/sthanika-ai/Sieve. The release stores the trained layers in full as a PEFT adapter (modulestosave), with a zero rank-1 LoRA on the embeddings. sieve 0.3.2 and later copy these layers into the backbone in place, so the model needs about the backbone's memory to load. probabilities. text-generation model. The backbone, Qwen/Qwen3.8-27B, is downloaded at its pinned revision (1d4bf0f2) on first use. our latency runs. One 80 GB GPU is enough; longer states need more. trainingconfig.json. Longer requests…
Read the full model card ↗ · Preview checked 2026-10-31T19:00:29.077Z
Inside the original model card — Document outline
- Sieve-27B-v2
- Summary
- How it works
- Use
- Results
- Decision Index
- Calibration
- Latency
- Training
- Limitations
- Files
- License
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
sthanika-ai/Sieve-27B-v2 is a text-classification model repository published by sthanika-ai 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-classification
- Library
- peft
- 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
- 2026-10-18T06:10:07.000Z
- Last modified
- 2026-10-18T06:17:10.000Z
Compatibility and lineage
Reported languages: en
Reported base models: Qwen/Qwen3.8-27B
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 2026-10-18T06:43:02.030Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.