interfaze-ai/lev
zero-shot-classification model by interfaze-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.
lev answers typed questions about a piece of context in a single forward pass. You give it a state (text, a ticket, an email, or JSON) and a set of yes/no, choice, and score questions. It reads each answer from the logits it already computed and returns calibrated probabilities over exactly the options you supplied. It is a LoRA adapter on Qwen3.5-4B, and it speaks TypeSafe's /v1/systemone protocol, so code written for the TypeSafe SDK works against it once you change the base URL. 74.3% on all 13 S1Bench subsets. 4B parameters. Zero output tokens. Qwen3.5-4B + LoRA on one H100. On the six subsets the public S1Bench board completed, behind only Jev and two open models of 26B and up, ahead of reflex-4b and a 35B model. Quickstart · Self-hosting · Benchmarks · Speed · Why it works · Training · Boundaries · GitHub No generated tokens, no JSON…
Read the full model card ↗ · Preview checked 2026-11-10T17:49:36.977Z
Inside the original model card — Document outline
- Installation
- Quickstart
- Self-hosting: a Jev-compatible HTTP server
- Benchmarks
- S1Bench
- Held-out split
- Speed
- Why it works
- The optimizations that mattered
- Training
- Boundaries worth understanding
- Hosted classification
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
interfaze-ai/lev is a zero-shot-classification model repository published by interfaze-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
- zero-shot-classification
- Library
- peft
- Recent downloads (30 days)
- 612
- Cumulative likes
- 108
- Hugging Face trending score
- 82
- Reported safetensors parameters
- Not reported
- Architecture
- Not reported
- License
- apache-2.0
- Access
- Not gated by Hugging Face
- Created
- 2026-09-24T06:33:36.000Z
- Last modified
- 2026-10-02T00:02:03.000Z
Compatibility and lineage
Reported languages: en
Reported base models: Qwen/Qwen3.5-4B
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 2026-10-03T06:38:34.100Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.