jaredpalmer/kev-4b

text-classification model by jaredpalmer

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.

Kev-4B is a decision model. It reads one document (the state) and a set of typed questions about it, and returns a calibrated probability distribution over the options supplied with each question, in a single forward pass and without generating text. It is intended for developers who classify, route, triage or check documents and who need probabilities that can be thresholded, for example to send uncertain cases to human review. It implements TypeSafe's public System One API (POST /v1/systemone), so the TypeSafe SDK works against it unchanged. It is a LoRA adapter and a pointer head on Qwen3.5-4B-Base, small enough for one 24 GB GPU or a 32 GB Apple Silicon Mac. This card describes the checkpoint in Kev 1.0, first published on 2026-09-24. Input. A state (text, or a JSON object or array rendered as labelled text) and any number of named questions, each of one of three types:…

jaredpalmer/kev-4b on Hugging Face A short preview, not the full document.

Read the full model card ↗ · Preview checked 2026-11-10T18:01:36.291Z

Inside the original model card — Document outline
  1. Kev-4B
  2. Model summary
  3. Model details
  4. Intended uses
  5. Out-of-scope uses
  6. How to use
  7. Training data
  8. Training procedure
  9. Evaluation
  10. Limitations and trade-offs
  11. Bias, risks and ethical considerations
  12. Compute

Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.

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

jaredpalmer/kev-4b is a text-classification model repository published by jaredpalmer 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)
14,133
Cumulative likes
97
Hugging Face trending score
51
Reported safetensors parameters
Not reported
Architecture
Not reported
License
apache-2.0
Access
Not gated by Hugging Face
Created
2026-09-19T03:59:43.000Z
Last modified
2026-10-01T17:18:26.000Z

Compatibility and lineage

Reported languages: en

Reported base models: Qwen/Qwen3.5-4B-Base

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 2026-10-02T06:38:30.819Z. 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

BAAI/bge-reranker-v2-m3

meta-llama/Prompt-Guard-86M

SamLowe/roberta-base-go_emotions

BAAI/bge-reranker-base

ProsusAI/finbert

autotrust/JEV-35B