Update 8B model card

README.md

@@ -38,25 +38,21 @@ L2-normalized multi-vector embeddings for late-interaction retrieval.
 The model uses bidirectional attention in Qwen3.5's full-attention layers and
 a learned 640-dimensional projection head. The unused language-model head has
 been removed from the released checkpoint. Consequently, the released
-embedding model contains 8,395,317,104 parameters, reflected by the
+embedding model contains ~8.4B parameters, reflected by the
 `webAI-ColVec1.1-8b` repository name, while its original backbone is
 Qwen3.5-9B.
 
 ### Training data
 
-We created filtered, balanced, and multilingual curated subsets from the six
-public datasets below. **This Qwen3.5-9B-backbone model was trained on a
-750,000-sample curated subset.** The companion 4B model was trained on a
-separate 500,000-sample curated subset.
-
-| Dataset source |
-| :--- |
-| [ColPali Train Set](https://huggingface.co/datasets/vidore/colpali_train_set) |
-| [Docmatix-IR](https://huggingface.co/datasets/Tevatron/docmatix-ir) |
-| [VisRAG In-Domain](https://huggingface.co/datasets/openbmb/VisRAG-Ret-Train-In-domain-data) |
-| [VisRAG Synthetic](https://huggingface.co/datasets/openbmb/VisRAG-Ret-Train-Synthetic-data) |
-| [VDR Multilingual Train](https://huggingface.co/datasets/llamaindex/vdr-multilingual-train) |
-| [Wiki-SS-NQ](https://huggingface.co/datasets/Tevatron/wiki-ss-nq) |
+We created filtered, balanced, and multilingual curated subsets from six public
+datasets: [ColPali Train Set](https://huggingface.co/datasets/vidore/colpali_train_set),
+[Docmatix-IR](https://huggingface.co/datasets/Tevatron/docmatix-ir),
+[VisRAG In-Domain](https://huggingface.co/datasets/openbmb/VisRAG-Ret-Train-In-domain-data),
+[VisRAG Synthetic](https://huggingface.co/datasets/openbmb/VisRAG-Ret-Train-Synthetic-data),
+[VDR Multilingual Train](https://huggingface.co/datasets/llamaindex/vdr-multilingual-train),
+and [Wiki-SS-NQ](https://huggingface.co/datasets/Tevatron/wiki-ss-nq). This
+Qwen3.5-9B-backbone model was trained on a 750,000-sample curated subset as well
+as synthetically generated data.
 
 ## 🛠️ Model specifications
 
@@ -84,10 +80,9 @@ separate 500,000-sample curated subset.
 
 ## 📊 Evaluation results
 
-The table reports NDCG@10 × 100 on the eight **public** ViDoRe V3 tasks. Private
-Nuclear and Telecom scores are intentionally omitted and will be added after
-official evaluation. Each task value is the mean of its six language subsets;
-the public average is the unweighted mean of the eight public task values.
+The table reports NDCG@10 scores on the eight **public** ViDoRe V3 tasks as
+percentages rather than values between 0 and 1 (for example, 0.80 is shown as
+80.00). Each task value is the mean of its six language subsets; the public average is the unweighted mean of the eight public task values.
 
 The result artifacts record MTEB 2.18.5, Transformers 5.14.1, PyTorch 2.9.0
 with CUDA 12.8, `bfloat16`, FlashAttention 2.8.3, and batch size 32. The release
@@ -100,8 +95,8 @@ Model encoding runs in `bfloat16`. Before MaxSim scoring, query and document
 embeddings are moved to CPU and converted to `float32`. All reported ViDoRe
 results use this FP32 scoring path.
 
-| Model | CompSci | Energy | FinanceEn | FinanceFr | HR | Industrial | Pharma | Physics | **Avg. public** |
-| :--- | ---: | ---: | ---: | ---: | ---: | ---: | ---: | ---: | ---: |
+| Model | Computer Science | Energy | FinanceEn | FinanceFr | HR | Industrial | Pharmaceuticals | Physics | **Avg. public** |
+| :--- | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: |
 | **webAI-ColVec1.1-8b (this model)** | 80.14 | 70.09 | **71.89** | **55.10** | 68.49 | **57.41** | 67.88 | 51.29 | **65.29** |
 | [VultronRetriever Prime](https://huggingface.co/vultr/VultronRetrieverPrime-Qwen3.5-8B) | 79.81 | **70.26** | 69.01 | 54.51 | 66.82 | **57.41** | **68.19** | **51.73** | 64.72 |
 | [webAI-ColVec1-9b](https://huggingface.co/webAI-Official/webAI-ColVec1-9b) | **80.92** | 69.77 | 68.28 | 53.72 | **70.04** | 57.18 | 67.32 | 48.38 | 64.45 |
@@ -238,18 +233,18 @@ change retrieval scores.
 
 ### Strengths
 
-- Strong public-task performance on ViDoRe V3.
-- OCR-free retrieval over visually complex document pages.
-- Fine-grained MaxSim matching with compact 640-dimensional token vectors.
-- Multilingual training data and evaluation.
-- FlashAttention 2 support across compatible CUDA GPUs and optimized
-  FlashAttention 3 inference on Hopper GPUs.
+- **Performance:** State-of-the-art retrieval performance on the public ViDoRe
+  V3 tasks, with excellent multimodal document retrieval results.
+- **Complex layouts:** Excellent handling of chart-rich PDFs and
+  domain-specific documents.
+- **End-to-end retrieval:** OCR-free retrieval on unseen multimodal documents
+  without using an intermediate vision-language model to generate summaries.
+- **Multilingualism:** Strong performance on non-English document inputs.
 
 ### Limitations
 
-- Multi-vector indexes require more storage than single-vector embeddings.
-- Scores can vary slightly between FlashAttention 2, FlashAttention 3, and
-  SDPA.
+- **Storage Cost:** Still larger than single-vector baselines despite the
+  smaller token dimension.
 
 ## License