Results for "visual-document-retrieval"

50 matches found.

jinaai

jinaai/jina-embeddings-v4

No description available.

📑 visual-document-retrieval 234,241
vidore

vidore/colqwen2-v0.1

No description available.

📑 visual-document-retrieval 117,202
vidore

vidore/colqwen2-v1.0

No description available.

📑 visual-document-retrieval 114,863
vidore

vidore/colqwen2-v1.0-hf

Read the `transformers` 🤗 model card: https://huggingface.co/docs/transformers/en/modeldoc/colqwen2....

📑 visual-document-retrieval 84,668
nvidia

nvidia/nemotron-colembed-vl-4b-v2

No description available.

📑 visual-document-retrieval 61,121
TomoroAI

TomoroAI/tomoro-colqwen3-embed-8b

No description available.

📑 visual-document-retrieval 47,647
vidore

vidore/colpali-v1.3

This model is built iteratively starting from an off-the-shelf SigLIP model. We finetuned it to create BiSigLIP and fed the patch-embeddings...

📑 visual-document-retrieval 44,291
jinaai

jinaai/jina-embeddings-v4-vllm-retrieval

This repository hosts a vLLM-compatible version of `jina-embeddings-v4` with the retrieval adapter merged into the base `Qwen2.5-VL` weights...

📑 visual-document-retrieval 40,573
vidore

vidore/colqwen2.5-v0.2

No description available.

📑 visual-document-retrieval 36,419
TomoroAI

TomoroAI/tomoro-colqwen3-embed-4b

No description available.

📑 visual-document-retrieval 26,362
vidore

vidore/colqwen-omni-v0.1

No description available.

📑 visual-document-retrieval 25,792
vidore

vidore/colpali-v1.2

This model is built iteratively starting from an off-the-shelf SigLIP model. We finetuned it to create BiSigLIP and fed the patch-embeddings...

📑 visual-document-retrieval 24,875
OpenSearch-AI

OpenSearch-AI/Ops-Colqwen3-4B

No description available.

📑 visual-document-retrieval 21,027
nvidia

nvidia/llama-nemotron-colembed-vl-3b-v2

No description available.

📑 visual-document-retrieval 13,516
ApsaraStackMaaS

ApsaraStackMaaS/EvoQwen2.5-VL-Retriever-7B-v1

EvoQwen2.5-VL-Retriever-7B-v1 is a high-performance multimodal retrieval model built upon the Qwen2.5-VL-7B-Instruct backbone and employing ...

📑 visual-document-retrieval 12,813
nvidia

nvidia/llama-nemoretriever-colembed-1b-v1

No description available.

📑 visual-document-retrieval 10,961
tsystems

tsystems/colqwen2.5-3b-multilingual-v1.0

No description available.

📑 visual-document-retrieval 9,980
nvidia

nvidia/llama-nemotron-rerank-vl-1b-v2

No description available.

📑 visual-document-retrieval 8,248
MrLight

MrLight/dse-qwen2-2b-mrl-v1

No description available.

📑 visual-document-retrieval 7,836
nomic-ai

nomic-ai/colnomic-embed-multimodal-7b

No description available.

📑 visual-document-retrieval 5,350
vidore

vidore/colpali

This model is built iteratively starting from an off-the-shelf SigLIP model. We finetuned it to create BiSigLIP and fed the patch-embeddings...

📑 visual-document-retrieval 4,637
vidore

vidore/colpali-v1.3-hf

Read the `transformers` 🤗 model card: https://huggingface.co/docs/transformers/en/modeldoc/colpali....

📑 visual-document-retrieval 3,912
nvidia

nvidia/nemotron-colembed-vl-8b-v2

No description available.

📑 visual-document-retrieval 3,258
TomoroAI

TomoroAI/tomoro-ai-colqwen3-embed-4b-awq

| Property | Value | |----| | Original Model | TomoroAI/tomoro-colqwen3-embed-4b | | Parameters | 4.0B | | Quantization | W4A16 (4-bit weigh...

📑 visual-document-retrieval 3,176
vidore

vidore/colpali-v1.2-hf

This model is built iteratively starting from an off-the-shelf SigLIP model. We finetuned it to create BiSigLIP and fed the patch-embeddings...

📑 visual-document-retrieval 3,033
jinaai

jinaai/jina-embeddings-v4-vllm-code

This repository hosts a vLLM-compatible version of `jina-embeddings-v4` with the code adapter merged into the base `Qwen2.5-VL` weights. Thi...

📑 visual-document-retrieval 2,488
ModernVBERT

ModernVBERT/colmodernvbert

No description available.

📑 visual-document-retrieval 2,442
nomic-ai

nomic-ai/colnomic-embed-multimodal-3b

No description available.

📑 visual-document-retrieval 2,093
Tevatron

Tevatron/OmniEmbed-v0.1

No description available.

📑 visual-document-retrieval 1,915
nomic-ai

nomic-ai/nomic-embed-multimodal-3b

No description available.

📑 visual-document-retrieval 1,909
vidore

vidore/colSmol-256M

No description available.

📑 visual-document-retrieval 1,457
lightonai

lightonai/MonoQwen2-VL-v0.1

The MonoQwen2-VL-v0.1 is a multimodal reranker finetuned with LoRA from Qwen2-VL-2B, optimized for asserting pointwise image-query relevance...

📑 visual-document-retrieval 1,261
vidore

vidore/colSmol-500M

No description available.

📑 visual-document-retrieval 1,144
nomic-ai

nomic-ai/nomic-embed-multimodal-7b

No description available.

📑 visual-document-retrieval 878
ModernVBERT

ModernVBERT/bimodernvbert

No description available.

📑 visual-document-retrieval 523
Haon-Chen

Haon-Chen/e5-omni-3B

No description available.

📑 visual-document-retrieval 508
vidore

vidore/colqwen2.5-v0.1

No description available.

📑 visual-document-retrieval 486
Metric-AI

Metric-AI/ColQwen2.5-3b-multilingual-v1.0

No description available.

📑 visual-document-retrieval 393
Cognitive-Lab

Cognitive-Lab/NetraEmbed

NetraEmbed is a multilingual multimodal embedding model that encodes both visual documents and text queries into single dense vectors. It su...

📑 visual-document-retrieval 374
jinaai

jinaai/jina-embeddings-v4-vllm-text-matching

This repository hosts a vLLM-compatible version of `jina-embeddings-v4` with the text-matching adapter merged into the base `Qwen2.5-VL` wei...

📑 visual-document-retrieval 369
vidore

vidore/colpali-v1.1

This model is built iteratively starting from an off-the-shelf SigLIP model. We finetuned it to create BiSigLIP and fed the patch-embeddings...

📑 visual-document-retrieval 317
Cognitive-Lab

Cognitive-Lab/ColNetraEmbed

ColNetraEmbed is a multilingual multimodal embedding model that encodes documents as multi-vector representations using the ColPali architec...

📑 visual-document-retrieval 303
Haon-Chen

Haon-Chen/e5-omni-7B

No description available.

📑 visual-document-retrieval 295
TomoroAI

TomoroAI/tomoro-ai-colqwen3-embed-8b-awq

| Property | Value | |----| | Original Model | TomoroAI/tomoro-colqwen3-embed-8b | | Parameters | 8.0B | | Quantization | W4A16 (4-bit weigh...

📑 visual-document-retrieval 269
Mungert

Mungert/Holo1-3B-GGUF

Holo1 is an Action Vision-Language Model (VLM) developed by HCompany for use in the Surfer-H web agent system. It is designed to interact wi...

📑 visual-document-retrieval 255
Metric-AI

Metric-AI/ColQwen2.5-7b-multilingual-v1.0

No description available.

📑 visual-document-retrieval 238
nvidia

nvidia/llama-nemoretriever-colembed-3b-v1

No description available.

📑 visual-document-retrieval 201
paultltc

paultltc/colmodernvbert_hf

No description available.

📑 visual-document-retrieval 164
vidore

vidore/colsmolvlm-v0.1

No description available.

📑 visual-document-retrieval 157
Mungert

Mungert/Holo1-7B-GGUF

Holo1 is an Action Vision-Language Model (VLM) developed by HCompany for use in the Surfer-H web agent system. It is designed to interact wi...

📑 visual-document-retrieval 149