Tag

Openjev

4 articles tagged with “Openjev”

The Paralon capybara holding two puzzle pieces that do not fit, a graphics card on the bench

Sep 24, 20265 min read

vLLM: "There is no module or parameter named 'visual' in Qwen3_5Model" — loading a Qwen3.5 classification head

Serving OpenJev (Qwen3_5ForSequenceClassification) on vLLM fails at weight loading because the checkpoint carries the vision tower and vLLM's fallback picks the text-only class. The fix is a text-only copy of the checkpoint. Also: 'UVA is not available' on WSL2, and why vllm serve cannot take a Hugging Face subfolder.

Read

Guides & Tutorials

Sep 23, 20267 min read

Catch RAG Hallucinations Sentence by Sentence with an NLI Classifier: 74 Planted Errors, 93% Caught, $0.013

A RAG pipeline on one API key: embeddings for retrieval, a 27B chat model for the answer, and OpenJev over /v1/classify to check every sentence of the answer against the passages it came from. We planted 74 wrong sentences in 148 answers so recall is exact: 93.2% caught at a 0.7 threshold, 4.6% of clean sentences flagged, 49 seconds and 1.3 cents for 463 sentences. The 27B used as a judge caught the same 69 for 2.4× the money and 3× the time. Script included.

Read

The Paralon capybara measuring three holographic bar columns with an emerald caliper, red cubes on the bench as the planted errors

Benchmarks & Comparisons

Sep 22, 20268 min read

OpenJev vs an LLM Judge on 990 Planted Errors: Recall, Calibration, Cost

The same 990 support tickets with 495 deliberately wrong labels, judged two ways: OpenJev over /v1/classify and Qwen 3.8 27B as an LLM judge. Asked one pair at a time OpenJev catches 82.6% of the planted errors; asked to pick among all twelve intents it catches 98.2%, rejects the same 33 mislabelled 'complaint' rows the 27B judge rejected, and its probabilities are calibrated to within 3 points. Every number is exact because we planted the errors.

Read

The Paralon capybara at a glowing emerald lever switch under holographic panels: one decision, no text

News & Updates

Sep 21, 20268 min read

OpenJev Is Live on an OpenAI-Compatible API: an Open Jev Alternative You Can Call Today

TypeSafe's Jev is hosted-only and behind a waitlist. OpenJev, the open NLI cross-encoder built on Qwen3.5, is now served on ParalonCloud behind POST /v1/classify: a label and calibrated probabilities per input, 3 ms per item in a batch, no generated text. Measured against a 27B LLM judge on the same pairs, with the vLLM recipe so you can run it yourself.

Read