No official torrent yet — requesting it tells the flock what to host next. You cannot seed a catalog-only page.
Cataloged from lightonai/LightOn-rerank-PW-4B
All models by lightonai →PW-0.8B | LW-0.8B | PW-2B | LW-2B | PW-4B | LW-4B
Production retrieval pipelines usually need two rerankers: one for text passages and one for visual documents (PDF pages, slides, scans). LightOn-rerank models are unified cross-encoder rerankers: a single model scores both text passages and document page images against a query, on top of any first-stage retriever (BM25, dense embeddings, or ColPali-family late-interaction models).
The models are built on Qwen3.5 backbone (hybrid linear + full attention) and jointly fine-tuned on text and visual reranking data with mixed-modality batches (LoRA, merged into the released weights). Training data is English-only; French performance transfers zero-shot from the multilingual backbone.
The family comes in two scoring flavours × three sizes (0.8B / 2B / 4B):
logit("Yes") − logit("No"). One forward pass per candidate and no generation.[2] > [4] > [1] > [3]). Larger candidate pools are ranked with a sliding window (window 4, stride 2, bottom-to-top). Cross-document attention makes LW markedly stronger on hard visual reranking, and unlike pointwise scoring it keeps improving with backbone size.LightOn-rerank-PW-4B is the 4B pointwise member of the family. On visual reranking it ties the 2B pointwise model (59.80 vs 59.87 nDCG@10 on ViDoRe V3): direct evidence that independent Yes/No scoring is a capacity bottleneck that extra parameters cannot fix. On text BEIR, however, it posts the strongest scores in the family (50.19 decontaminated mean). For 4B-budget vision-heavy deployments, LightOn-rerank-LW-4B is +4.9 nDCG@10 at the same size.
ViDoRe V3 (visual document reranking, 8 domains × EN/FR queries), overall nDCG@10, ColQwen2.5-v0.2 first stage, retrieve 100 / rerank 100. All models, including baselines, were re-evaluated under this same two-stage protocol, so numbers are mutually comparable but not comparable to vendor-reported end-to-end results.
Overall nDCG@10: 59.80 (EN 62.37 / FR 57.23).
13 datasets, nDCG@10, BM25 first stage, retrieve 100 / rerank 100, same protocol as all other family members. ⚠️ marks datasets in the text training mix (NQ, MSMARCO); the decontaminated mean excludes them.
This is the best text result in the LightOn-rerank family (2B pointwise: 49.13, 4B listwise: 48.33 decontaminated mean). Pointwise plateaus with scale on vision but not on text. If your workload is text-dominant and you have the 4B budget, this is the family's strongest text reranker.
logit("Yes") − logit("No"))[pos, neg_0, neg_1, neg_2] 4-list with hard negatives mined via the NV-Retriever approach with GTE-ModernBERT) + 106k vision groups (ColPali train set with negatives mined by Nomic). For pointwise training each group is flattened into (query, document, Yes/No) triples.transformers >= 5.4.0 (qwen3_5 architecture); sentence-transformers >= 5.4.0 for the CrossEncoder usageEach candidate is scored independently as logit("Yes") − logit("No") at the first generated position; sort candidates by descending score. The model was trained with a fixed system prompt and user template: use them verbatim for best results.
Install Sentence Transformers (>= 5.4.0):
The trained system prompt and user templates are baked into the bundled reranker chat template — including the non-thinking generation prompt, so no enable_thinking handling is needed — and query-document pairs are formatted correctly out of the box:
To rerank page images, pass a PIL.Image (or an image URL or file path string) as the document. Text and image candidates can be mixed in the same call:
Scores are raw logit("Yes") − logit("No") differences. You can map them to 0...1 probabilities with model.predict(pairs, activation_fn=torch.nn.Sigmoid()).
To score a page image instead of a text passage, replace the user message with:
and pass images=[page_image, ...] to the processor call (keep the same system prompt).
Full-page document images can exceed 8k tokens, so keep --max-model-len at 16384 or higher when reranking page images.
<think> by default; with it on, the first generated token is a thinking token and the Yes/No logprobs are distorted. Pass enable_thinking=False to apply_chat_template (or chat_template_kwargs={"enable_thinking": False} via the vLLM OpenAI client) as shown above. The Sentence Transformers path handles this automatically: the bundled reranker chat template hardcodes the non-thinking generation prompt.Rule of thumb: LW models are stronger at every size (and the gap grows with size); PW models are cheaper to serve and score candidates independently. For the best quality pick LW-4B; for the best quality/cost trade-off pick LW-2B; for maximum throughput on text-heavy workloads pick a PW model.
pip install "sentence-transformers[image]"from sentence_transformers import CrossEncoder
model = CrossEncoder("lightonai/LightOn-rerank-PW-4B")
query = "What is late interaction in neural information retrieval?"documents = [ "ColBERT computes token-level query-document interactions at search time...", "The Eiffel Tower is located on the Champ de Mars in Paris.",]
pairs = [(query, doc) for doc in documents]scores = model.predict(pairs)print(scores)# [-3. -8.0625]
rankings = model.rank(query, documents)print(rankings)# [{'corpus_id': 0, 'score': -3.0}, {'corpus_id': 1, 'score': -8.0625}]from PIL import Image
pairs = [ (query, Image.open("page_1.png")), (query, "https://example.com/page_2.png"), (query, "A text passage candidate for the same query."),]scores = model.predict(pairs)import torchfrom transformers import AutoModelForImageTextToText, AutoProcessor
model_id = "lightonai/LightOn-rerank-PW-4B"model = AutoModelForImageTextToText.from_pretrained( model_id, dtype=torch.bfloat16, attn_implementation="flash_attention_2", # optional, remove if flash-attn is not installed device_map="cuda",).eval()processor = AutoProcessor.from_pretrained(model_id)processor.tokenizer.padding_side = "left" # scores are read at the last position
YES_TOKEN_ID = 9175 # "Yes"NO_TOKEN_ID = 2665 # "No"
SYSTEM_PROMPT = "Judge whether the document is relevant to the query. Answer Yes or No."USER_TEMPLATE = ( "Given a query, determine if the document is relevant. " "The query is: {query}\n\nDocument: {doc}")
query = "What is late interaction in neural information retrieval?"documents = [ "ColBERT computes token-level query-document interactions at search time...", "The Eiffel Tower is located on the Champ de Mars in Paris.",]
texts = [ processor.apply_chat_template( [ {"role": "system", "content": SYSTEM_PROMPT}, {"role": "user", "content": USER_TEMPLATE.format(query=query, doc=doc)}, ], tokenize=False, add_generation_prompt=True, enable_thinking=False, # REQUIRED on the 4B backbone (thinking on by default) ) for doc in documents]inputs = processor( text=texts, return_tensors="pt", padding=True, truncation=True, max_length=2048).to(model.device)with torch.inference_mode(): logits = model(**inputs).logits[:, -1]scores = (logits[:, YES_TOKEN_ID] - logits[:, NO_TOKEN_ID]).tolist()# [-3.0, -8.0625]
ranked = sorted(zip(scores, documents), reverse=True)VISION_TEMPLATE = "Given a query, determine if the document image is relevant. The query is: {query}"
{"role": "user", "content": [ {"type": "image", "image": page_image}, # PIL.Image {"type": "text", "text": VISION_TEMPLATE.format(query=query)},]}vllm serve lightonai/LightOn-rerank-PW-4B --trust-remote-code --max-model-len 16384resp = client.chat.completions.create( model="lightonai/LightOn-rerank-PW-4B", messages=messages, # same system + user messages as above max_tokens=1, logprobs=True, top_logprobs=20, temperature=0.0, extra_body={"chat_template_kwargs": {"enable_thinking": False}}, # REQUIRED)top = resp.choices[0].logprobs.content[0].top_logprobslp = {t.token: t.logprob for t in top}score = lp.get("Yes", -100.0) - lp.get("No", -100.0)@misc{ananya2026lightonrerank, title={One Adapter, Both Modalities: Field Notes from Building and Serving a Multimodal Reranker}, author={Ananya, Ishrat Jahan and Chatelain, Amelie}, year={2026}, howpublished={\url{https://huggingface.co/blog/lightonai/lighton-rerank}},}