spock-oss/sel-qwen-27b

AI model by spock-oss

Open original source ↗

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.

SEL takes source text, an image, or both, plus one or more questions. It returns scores and selected positions in the original input. A single Qwen backbone pass supplies hidden states to a dense scorer or a pointer head. The linked pointer can condition a later selection on an earlier one. GitHub code · Research blog · Training dataset Install the standalone SEL CLI using the GitHub README. The CLI uses the pinned Qwen 3.8 27B base revision, loads the frozen language weights in NF4, and applies this rank-16 LoRA and the selection head. The release bundle is approximately 480 MB. The separate base snapshot is approximately 56 GB on disk. Use --text-file for a document, --image for an image, and repeat --query for multiple questions. The output includes per-question scores and selected source indices, with character…

spock-oss/sel-qwen-27b on Hugging Face A short preview, not the full document.

Read the full model card ↗ · Preview checked 2026-11-11T08:47:23.657Z

Inside the original model card — Document outline
  1. SEL Qwen 27B
  2. Run a selection
  3. What the files contain

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: mit. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.

Model overview

spock-oss/sel-qwen-27b is a task-unspecified model repository published by spock-oss on Hugging Face. A library was not reported.

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

Model facts

Task
Not reported
Library
Not reported
Recent downloads (30 days)
0
Cumulative likes
0
Hugging Face trending score
0
Reported safetensors parameters
Not reported
Architecture
Not reported
License
mit
Access
Not gated by Hugging Face
Created
2026-11-11T06:35:33.000Z
Last modified
2026-11-11T06:44:07.000Z

Compatibility and lineage

Language coverage was not reported.

Base-model lineage was not included.

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

Source and freshness

Source: Hugging Face Hub. Metadata observed 2026-11-11T06:56:43.242Z. Daily imports are snapshots, not real-time monitoring.

Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.

Open original source

Related models