Model card edits: hero image, nDCG@10 table headers, BEIR results section, decontaminated wording

.gitattributes

@@ -34,3 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 tokenizer.json filter=lfs diff=lfs merge=lfs -text
+rerank.png filter=lfs diff=lfs merge=lfs -text

README.md

@@ -40,6 +40,10 @@ tags:
 <a href="https://huggingface.co/lightonai/LightOn-rerank-LW-4B">LW-4B</a>
 </p>
 
+<div align="center">
+<img src="rerank.png" alt="Reranking: the second stage that puts the best text and image candidates on top" width="560">
+</div>
+
 ---
 
 ## About the LightOn-rerank family
@@ -50,16 +54,16 @@ The models are built on Qwen3.5 vision-language backbones (hybrid linear + full
 
 The family comes in two scoring flavours × three sizes (0.8B / 2B / 4B):
 
-- **PW (pointwise)** — each candidate is scored independently: the model judges whether the document answers the query, and the score is `logit("Yes") − logit("No")`. One forward pass per candidate, no generation — simple to serve (vLLM-compatible) and embarrassingly parallel.
-- **LW (listwise)** — generative listwise ranking: 4 candidates are placed in a single prompt and the model generates a permutation (`[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.
+- **PW (pointwise)**: each candidate is scored independently. The model judges whether the document answers the query, and the score is `logit("Yes") − logit("No")`. One forward pass per candidate and no generation, so it is simple to serve (vLLM-compatible) and embarrassingly parallel.
+- **LW (listwise)**: generative listwise ranking, where 4 candidates are placed in a single prompt and the model generates a permutation (`[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-2B** is the pointwise flagship of the family: a single 2B model that is simultaneously competitive with dedicated text rerankers on BEIR and with vision-specialised rerankers on ViDoRe V2/V3 — with none of the usual trade-off between the two modalities, and the serving simplicity of independent per-candidate scoring.
+**LightOn-rerank-PW-2B** is the pointwise flagship of the family: a single 2B model that is simultaneously competitive with dedicated text rerankers on BEIR and with vision-specialised rerankers on ViDoRe V2/V3, with none of the usual trade-off between the two modalities, and the serving simplicity of independent per-candidate scoring.
 
 ## Results
 
-**ViDoRe V3** (visual document reranking, 8 domains × EN/FR queries), 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.
+**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.
 
-| Model | Params | Scoring | ViDoRe V3 overall @10 |
+| Model | Params | Scoring | ViDoRe V3 overall nDCG@10 |
 |---|---|---|---|
 | [LightOn-rerank-LW-4B](https://huggingface.co/lightonai/LightOn-rerank-LW-4B) | 4.5B | listwise | 0.6469 |
 | *Qwen3-VL-Reranker-8B* | *8B* | *pointwise (pooling)* | *0.6423* |
@@ -71,7 +75,7 @@ The family comes in two scoring flavours × three sizes (0.8B / 2B / 4B):
 | [LightOn-rerank-LW-0.8B](https://huggingface.co/lightonai/LightOn-rerank-LW-0.8B) | 0.85B | listwise | 0.5825 |
 | [LightOn-rerank-PW-0.8B](https://huggingface.co/lightonai/LightOn-rerank-PW-0.8B) | 0.85B | pointwise | 0.4820 |
 
-### ViDoRe V3 detail (NDCG, ColQwen2.5 first stage, rerank-100)
+### ViDoRe V3 detail (nDCG, ColQwen2.5 first stage, rerank-100)
 
 | Domain | EN @5 | EN @10 | FR @5 | FR @10 |
 |---|---|---|---|---|
@@ -85,33 +89,34 @@ The family comes in two scoring flavours × three sizes (0.8B / 2B / 4B):
 | physics | 0.4551 | 0.4851 | 0.4568 | 0.4927 |
 | **mean** | **0.5906** | **0.6098** | **0.5676** | **0.5876** |
 
-Overall @10: **0.5987** (EN 0.6098 / FR 0.5876).
+Overall nDCG@10: **0.5987** (EN 0.6098 / FR 0.5876). On the easier ViDoRe V2 benchmark (same protocol), mean nDCG@10 is **0.8558**, in the same range as the strongest 2B-class baselines (jina-reranker-m0: 0.8596, MonoQwen2-VL-v0.1: 0.8454, Qwen3-VL-Reranker-2B: 0.8428).
 
-### Other benchmarks (same fixed-first-stage protocol)
+### BEIR results (text reranking)
 
-| Benchmark | LightOn-rerank-PW-2B | Best 2B-class baseline |
-|---|---|---|
-| ViDoRe V2, mean NDCG@10 (ColQwen2.5 first stage) | 0.8558 | jina-reranker-m0: 0.8596; MonoQwen2-VL-v0.1: 0.8454; Qwen3-VL-Reranker-2B: 0.8428 |
-| BEIR 15 datasets, clean mean NDCG@10 (jina-embeddings-v3 first stage) | 0.5227 | jina-reranker-m0: 0.5677; Qwen3-VL-Reranker-2B: 0.5025 |
-| BEIR 15 datasets, clean mean NDCG@10 (BM25 first stage) | 0.4968 | jina-reranker-m0: 0.5397; Qwen3-VL-Reranker-2B: 0.4815 |
+15 datasets, nDCG@10, retrieve 100 / rerank 100, all models re-evaluated under the same protocol. The decontaminated mean excludes NQ and MSMARCO (present in the training data).
+
+| First stage | LightOn-rerank-PW-2B | jina-reranker-m0 | Qwen3-VL-Reranker-2B |
+|---|---|---|---|
+| jina-embeddings-v3 (decontaminated mean) | 0.5227 | **0.5677** | 0.5025 |
+| BM25 (decontaminated mean) | 0.4968 | **0.5397** | 0.4815 |
 
-Clean mean excludes the two contaminated datasets (NQ, MSMARCO). On text it sits between the two strongest 2B baselines; on visual reranking it matches or beats every 2B-class model — jina-reranker-m0 is the only baseline that is close on both, and it trails on ViDoRe V3 (0.5939 vs 0.5987).
+On text it sits between the two strongest 2B baselines. jina-reranker-m0 is the only baseline that is close on both modalities, and it trails on ViDoRe V3 (0.5939 vs 0.5987).
 
 ## Model Details
 
-- **Model type:** multimodal cross-encoder reranker — **pointwise**: each candidate is scored independently as `logit("Yes") − logit("No")`
+- **Model type:** multimodal cross-encoder reranker (**pointwise**: each candidate is scored independently as `logit("Yes") − logit("No")`)
 - **Base model:** [Qwen/Qwen3.5-2B](https://huggingface.co/Qwen/Qwen3.5-2B) (Qwen3.5 hybrid linear + full attention VLM)
 - **Parameters:** ≈2.2B (bfloat16, 4.4 GB)
-- **Inputs:** query (text) + candidate document(s) — text passage **or** page image
-- **Fine-tuning:** joint text+vision LoRA (r=32, α=32, rsLoRA — merged into the released weights), mixed-modality batches (2 text + 2 vision groups per micro-batch), vision loss weight 1.3, lr 1e-4, 1 epoch (465 steps)
+- **Inputs:** query (text) + candidate document(s): text passage **or** page image
+- **Fine-tuning:** joint text+vision LoRA (r=32, α=32, rsLoRA, merged into the released weights), mixed-modality batches (2 text + 2 vision groups per micro-batch), vision loss weight 1.3, lr 1e-4, 1 epoch (465 steps)
 - **Data:** ~120k EN text queries (NQ, TriviaQA, MSMARCO) with mined hard negatives + ~118k visual query–page pairs with ColPali-family hard negatives (`dedup_120k_en_v3` + `ColPali_hard_neg_v2`)
 - **Languages:** English (training), French (zero-shot transfer)
 - **Requirements:** `transformers >= 5.4.0` (`qwen3_5` architecture)
 - **Internal experiment ID:** `exp30`
 
-## Usage — pointwise reranking
+## Usage: pointwise reranking
 
-Each 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.
+Each 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.
 
 ```python
 import torch
@@ -121,7 +126,7 @@ model_id = "lightonai/LightOn-rerank-PW-2B"
 model = AutoModelForImageTextToText.from_pretrained(
     model_id,
     dtype=torch.bfloat16,
-    attn_implementation="flash_attention_2",  # optional — remove if flash-attn is not installed
+    attn_implementation="flash_attention_2",  # optional, remove if flash-attn is not installed
     device_map="cuda",
 ).eval()
 processor = AutoProcessor.from_pretrained(model_id)
@@ -198,18 +203,17 @@ lp = {t.token: t.logprob for t in top}
 score = lp.get("Yes", -100.0) - lp.get("No", -100.0)
 ```
 
-Full-page document images can exceed 8k tokens — keep `--max-model-len` at 16384 or higher when reranking page images.
+Full-page document images can exceed 8k tokens, so keep `--max-model-len` at 16384 or higher when reranking page images.
 
 ## Notes & limitations
 
-- Pointwise scoring does not improve with backbone scale (the 4B pointwise model ties this one) — if you have the compute budget, [LightOn-rerank-LW-2B](https://huggingface.co/lightonai/LightOn-rerank-LW-2B) is +0.03 NDCG@10 on ViDoRe V3 at the same size.
+- Pointwise scoring does not improve with backbone scale (the 4B pointwise model ties this one). If you have the compute budget, [LightOn-rerank-LW-2B](https://huggingface.co/lightonai/LightOn-rerank-LW-2B) is +0.03 nDCG@10 on ViDoRe V3 at the same size.
 - Training data is English-only. French works zero-shot (the backbone is multilingual) but is slightly behind English on average.
-- Vision hard negatives were mined with ColPali-family retrievers; the model pairs best with a ColPali-family first stage (e.g. ColQwen2.5) for visual reranking.
-- BEIR contamination flag: NQ and MSMARCO are part of the text training data; headline text figures use clean means that exclude them.
+- BEIR contamination flag: NQ and MSMARCO are part of the text training data; headline text figures use decontaminated means that exclude them.
 
 ## The LightOn-rerank family
 
-| Model | Backbone | Scoring | ViDoRe V3 @10 |
+| Model | Backbone | Scoring | ViDoRe V3 overall nDCG@10 |
 |---|---|---|---|
 | [LightOn-rerank-PW-0.8B](https://huggingface.co/lightonai/LightOn-rerank-PW-0.8B) | Qwen3.5-0.8B | pointwise | 0.4820 |
 | [LightOn-rerank-LW-0.8B](https://huggingface.co/lightonai/LightOn-rerank-LW-0.8B) | Qwen3.5-0.8B | listwise | 0.5825 |