SuperbPiggy/trace-qwen3-vl-4b-loo-fca
AI model by SuperbPiggy
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.
license: apache-2.0 basemodel: Qwen/Qwen3-VL-4B-Instruct libraryname: peft tags: Project overview · Quickstart This release contains only the TRACE LoRA adapter for Qwen3-VL-4B with FCA held out. It does not include the Qwen base model, SAM 3 weights, training data, optimizer state, or training logs. It is not a standalone model and does not represent all nine leave-one-out checkpoints or the task-specific models used in the main results table. The training manifest and the original training log were checked together. The source counts are: FCA exclusion applies to this TRACE fine-tuning manifest, not to an audit of the upstream base model's pretraining corpus. Download the adapter files directly from this Hugging Face repository. Clone the repository or use snapshotdownload to get a local folder containing adaptermodel.safetensors, adapterconfig.json, this model card, trainingmanifest.json with aggregate provenance, license notices, and SHA256SUMS. The adapter tensors are unchanged from the source checkpoint; only the configuration's base-model reference…
Read the full model card ↗ · Preview checked 2026-10-28T23:10:40.856Z
Inside the original model card — Document outline
- TRACE · Qwen3-VL-4B LOO adapter
- - arrowhead-extraction
- Model and training provenance
- Download and verify
- Load with PEFT
- Recorded evaluation
- License and limitations
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. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
SuperbPiggy/trace-qwen3-vl-4b-loo-fca is a task-unspecified model repository published by SuperbPiggy 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
- Not reported — check the model card
- Access
- Not gated by Hugging Face
- Created
- 2026-10-09T06:35:09.000Z
- Last modified
- 2026-10-09T06:35:20.000Z
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.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-10-09T06:40:49.674Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.