colpali
vidore基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
기본 정보 등록 · 상세 정보 보완 예정
입력 미확인→ 출력 미확인
요금 미확인멀티모달 및 채널 요금 별도 확인
자세히 보기 ↗DISCOVER & COMPARE
AI 모델 탐색 13
colpali-v1.2
vidoreColPali is a model based on a novel model architecture and training strategy based on Vision Language Models (VLMs) to efficiently index documents from their visual features. It is a PaliGemma-3B extension that generates ColBERT- style multi-vector representations of text and images. It was introduced in the paper ColPali: Efficient Document Retrieval with Vision Language Models and first released in this repository This version is trained with `colpali-engine==0.2.0` but can be loaded for any version `>=0.2.0`. Compared to `vidore/colpali`, this version is trained with right padding for queries to fix unwanted tokens in the query encoding. It also stems from the fixed `vidore/colpaligemma-3b-pt-448-base` to guarantee deterministic projection layer initialization. It was trained for 5 epochs, with in-batch negatives and hard mined negatives and a warmup of 1000 steps (10x longer) to help reduce non-english language collapse.
번역 대기 중 · 원문 표시
입력 미확인→ 출력 미확인
요금 미확인멀티모달 및 채널 요금 별도 확인
자세히 보기 ↗colpali-v1.2-hf
vidore基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
입력 미확인→ 출력 미확인
요금 미확인멀티모달 및 채널 요금 별도 확인
자세히 보기 ↗colpali-v1.3
vidoreColPali is a model based on a novel model architecture and training strategy based on Vision Language Models (VLMs) to efficiently index documents from their visual features. It is a PaliGemma-3B extension that generates ColBERT- style multi-vector representations of text and images. It was introduced in the paper ColPali: Efficient Document Retrieval with Vision Language Models and first released in this repository Compared to `vidore/colpali`, this version is trained with right padding for queries to fix unwanted tokens in the query encoding. It also stems from the fixed `vidore/colpaligemma-3b-pt-448-base` to guarantee deterministic projection layer initialization. It was trained for 5 epochs, with in-batch negatives and hard mined negatives and a warmup of 1000 steps (10x longer) to help reduce non-english language collapse. This model is built iteratively starting from an off-the-shelf SigLIP model. We finetuned it to create BiSigLIP and fed the patch-embeddings output by SigLIP to an LLM, PaliGemma-3B to create BiPali.
번역 대기 중 · 원문 표시
입력 미확인→ 출력 미확인
요금 미확인멀티모달 및 채널 요금 별도 확인
자세히 보기 ↗colpali-v1.3-hf
vidore> [!IMPORTANT] > This version of ColPali should be loaded with the `transformers 🤗` release or Sentence Transformers, not with `colpali-engine`. > It was converted using the `convert_colpali_weights_to_hf.py` script > from the `vidore/colpali-v1.3-merged` checkpoint. ColPali is a model based on a novel model architecture and training strategy based on Vision Language Models (VLMs) to efficiently index documents from their visual features. It is a PaliGemma-3B extension that generates ColBERT- style multi-vector representations of text and images. It was introduced in the paper ColPali: Efficient Document Retrieval with Vision Language Models and first released in this repository The HuggingFace `transformers` 🤗 implementation was contributed by Tony Wu (@tonywu71) and Yoni Gozlan (@yonigozlan).
번역 대기 중 · 원문 표시
입력 미확인→ 출력 미확인
요금 미확인멀티모달 및 채널 요금 별도 확인
자세히 보기 ↗colpali-v1.3-merged
vidore基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
입력 미확인→ 출력 미확인
요금 미확인멀티모달 및 채널 요금 별도 확인
자세히 보기 ↗colqwen2.5-v0.2
vidoreColQwen is a model based on a novel model architecture and training strategy based on Vision Language Models (VLMs) to efficiently index documents from their visual features. It is a Qwen2.5-VL-3B extension that generates ColBERT- style multi-vector representations of text and images. It was introduced in the paper ColPali: Efficient Document Retrieval with Vision Language Models and first released in this repository This model takes dynamic image resolutions in input and does not resize them, changing their aspect ratio as in ColPali. Maximal resolution is set so that 768 image patches are created at most. Experiments show clear improvements with larger amounts of image patches, at the cost of memory requirements. Our training dataset of 127,460 query-page pairs is comprised of train sets of openly available academic datasets (63%) and a synthetic dataset made up of pages from web-crawled PDF documents and augmented with VLM-generated (Claude-3 Sonnet) pseudo-questions (37%). Our training set is fully English by design, enabling us to study zero-shot generalization to non-English languages. We explicitly verify no multi-page PDF document is used both *ViDoRe* and in the train set to prevent evaluation contamination. A validation set is created with 2% of the samples to tune hyperparameters.
번역 대기 중 · 원문 표시
입력 미확인→ 출력 미확인
요금 미확인멀티모달 및 채널 요금 별도 확인
자세히 보기 ↗colqwen2-v0.1
vidore基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
입력 미확인→ 출력 미확인
요금 미확인멀티모달 및 채널 요금 별도 확인
자세히 보기 ↗colqwen2-v1.0
vidoreColQwen2 is a model based on a novel model architecture and training strategy based on Vision Language Models (VLMs) to efficiently index documents from their visual features. It is a Qwen2-VL-2B extension that generates ColBERT- style multi-vector representations of text and images. It was introduced in the paper ColPali: Efficient Document Retrieval with Vision Language Models and first released in this repository This model takes dynamic image resolutions in input and does not resize them, changing their aspect ratio as in ColPali. Maximal resolution is set so that 768 image patches are created at most. Experiments show clear improvements with larger amounts of image patches, at the cost of memory requirements. Our training dataset of 127,460 query-page pairs is comprised of train sets of openly available academic datasets (63%) and a synthetic dataset made up of pages from web-crawled PDF documents and augmented with VLM-generated (Claude-3 Sonnet) pseudo-questions (37%). Our training set is fully English by design, enabling us to study zero-shot generalization to non-English languages. We explicitly verify no multi-page PDF document is used both *ViDoRe* and in the train set to prevent evaluation contamination. A validation set is created with 2% of the samples to tune hyperparameters.
번역 대기 중 · 원문 표시
입력 미확인→ 출력 미확인
요금 미확인멀티모달 및 채널 요금 별도 확인
자세히 보기 ↗colqwen2-v1.0-hf
vidore> [!IMPORTANT] > This version of ColQwen2 should be loaded with the `transformers 🤗` release or Sentence Transformers, not with `colpali-engine`. > It was converted using the `convert_colqwen2_weights_to_hf.py` script > from the `vidore/colqwen2-v1.0-merged` checkpoint. ColQwen2 is a model based on a novel model architecture and training strategy based on Vision Language Models (VLMs) to efficiently index documents from their visual features. It is a Qwen2-VL-2B extension that generates ColBERT- style multi-vector representations of text and images. It was introduced in the paper ColPali: Efficient Document Retrieval with Vision Language Models and first released in this repository The HuggingFace `transformers` 🤗 implementation was contributed by Tony Wu (@tonywu71) and Yoni Gozlan (@yonigozlan).
번역 대기 중 · 원문 표시
입력 미확인→ 출력 미확인
요금 미확인멀티모달 및 채널 요금 별도 확인
자세히 보기 ↗colSmol-256M
vidoreColSmolVLM is a model based on a novel model architecture and training strategy based on Vision Language Models (VLMs) to efficiently index documents from their visual features. It is a SmolVLM extension that generates ColBERT- style multi-vector representations of text and images. It was introduced in the paper ColPali: Efficient Document Retrieval with Vision Language Models and first released in this repository This version is trained with the commit b983e40 of the Colpali repository. (main branch from the repo) Our training dataset of 127,460 query-page pairs is comprised of train sets of openly available academic datasets (63%) and a synthetic dataset made up of pages from web-crawled PDF documents and augmented with VLM-generated (Claude-3 Sonnet) pseudo-questions (37%). Our training set is fully English by design, enabling us to study zero-shot generalization to non-English languages. We explicitly verify no multi-page PDF document is used both *ViDoRe* and in the train set to prevent evaluation contamination. A validation set is created with 2% of the samples to tune hyperparameters.
번역 대기 중 · 원문 표시
입력 미확인→ 출력 미확인
요금 미확인멀티모달 및 채널 요금 별도 확인
자세히 보기 ↗colSmol-500M
vidoreColSmolVLM is a model based on a novel model architecture and training strategy based on Vision Language Models (VLMs) to efficiently index documents from their visual features. It is a SmolVLM extension that generates ColBERT- style multi-vector representations of text and images. It was introduced in the paper ColPali: Efficient Document Retrieval with Vision Language Models and first released in this repository This version is trained with the commit b983e40 of the Colpali repository. (main branch from the repo) Our training dataset of 127,460 query-page pairs is comprised of train sets of openly available academic datasets (63%) and a synthetic dataset made up of pages from web-crawled PDF documents and augmented with VLM-generated (Claude-3 Sonnet) pseudo-questions (37%). Our training set is fully English by design, enabling us to study zero-shot generalization to non-English languages. We explicitly verify no multi-page PDF document is used both *ViDoRe* and in the train set to prevent evaluation contamination. A validation set is created with 2% of the samples to tune hyperparameters.
번역 대기 중 · 원문 표시
입력 미확인→ 출력 미확인
요금 미확인멀티모달 및 채널 요금 별도 확인
자세히 보기 ↗colsmolvlm-v0.1
vidore基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
기본 정보 등록 · 상세 정보 보완 예정
입력 미확인→ 출력 미확인
요금 미확인멀티모달 및 채널 요금 별도 확인
자세히 보기 ↗일치하는 모델 없음
제공사, 분류, 입출력 조건을 조정하세요. 새 모델이 계속 등록됩니다.
COST EXPLORER
좋은 모델, 명확한 비용.
월간 토큰 사용량으로 예상 API 비용을 비교하세요.
1 M = 100만 토큰 · USD
동일 채널의 기본 텍스트 토큰 요금 비교
동일 채널의 기본 텍스트 토큰 요금 비교
수집된 백만 토큰당 USD 요금입니다. 캐시 할인, 구간 요금, 추가 추론 출력, 세금은 제외됩니다. 최신 요금은 출처에서 확인하세요.
MODEL HANDBOOK
이해하고 선택하세요
API 요금은 어떻게 비교하나요?+
입력, 출력, 캐시 요금을 구분하고 동일 작업량으로 비교하세요. 이미지, 음성, 영상은 개수, 시간, 해상도로 과금될 수 있습니다.
오픈 웨이트는 무료 상업 이용을 뜻하나요?+
반드시 그렇지는 않습니다. 버전별 라이선스, 상업 이용 제한, 정책을 확인하세요. 자체 호스팅에는 연산 및 유지 비용도 듭니다.
1위 모델이 나에게 가장 적합한가요?+
순위는 작업, 버전, 평가 방식에 따라 다릅니다. 실제 업무로 정확도, 지연, 안정성, 비용을 비교하세요.