Agent-ModernColBERT
lightonai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。
基础资料已收录 · 缺失资料后续补充
输入 文本→ 输出 向量
价格待核验多模态与渠道费用须分别核对
查看详情 ↗DISCOVER & COMPARE
探索 AI 模型 38
answerai-colbert-small-v1
lightonaiThis is a answerdotai/answerai-colbert-small-v1 model converted to PyLate format. It maps sentences & paragraphs to sequences of 96-dimensional dense vectors and can be used for semantic textual similarity using the MaxSim operator. PyLate provides a streamlined interface to index and retrieve documents using ColBERT models. The index leverages the Voyager HNSW index to efficiently handle document embeddings and enable fast retrieval. First, load the ColBERT model and initialize the Voyager index, then encode and index your documents:
译文排队中 · 当前显示来源原文
输入 文本→ 输出 向量
价格待核验多模态与渠道费用须分别核对
查看详情 ↗ColBERT-Zero
lightonai> 🎯 **TL;DR**: First large-scale fully pre-trained ColBERT model using only public data. Achieves **55.43 nDCG@10** on BEIR benchmark, outperforming GTE-ModernColBERT and GTE-ModernBERT trained on closed and stronger data. **New SOTA on BEIR for models Nomic's base models are pre-trained with asymmetric prompts (`search_query:` and `search_document:`). While ColBERT has its own asymmetric mechanism via `[Q]` and `[D]` markers, we found: - **Stripping pre-training prompts during fine-tuning** causes significant performance degradation. - **Adding prompts to a model not pre-trained with them** also hurts performance. - **Even with perfect alignment**, prompts provide an intrinsic benefit: full ColBERT pre-training with prompts (55.43) vs. without prompts (54.61), no mismatch in either case, shows a meaningful 0.82-point gap. **Why do prompts help?** Our leading hypothesis is that prompt tokens act as **implicit query expansion**: extra slots that don't carry specific meaning but let the model store global information about the sequence. The original ColBERT used `[PAD]` tokens for this purpose, but modern Flash Attention implementations broke this trick (masked tokens no longer produce usable embeddings). Explicit prompt tokens may be quietly re-enabling it.
译文排队中 · 当前显示来源原文
输入 文本→ 输出 向量
价格待核验多模态与渠道费用须分别核对
查看详情 ↗colbertv2.0
lightonaiAll the credits belong to the original authors and we thank Omar Khattab for allowing us to share this version of the model. Please refer to the original repository and paper for more information about the model and to PyLate repository for information about usage of the model. This model can be used with Sentence Transformers as a multi-vector (ColBERT-style late interaction) retriever via the `MultiVectorEncoder`:
译文排队中 · 当前显示来源原文
输入 文本→ 输出 向量
价格待核验多模态与渠道费用须分别核对
查看详情 ↗colgrep-agent-2B
lightonai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。
基础资料已收录 · 缺失资料后续补充
输入 文本→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗colgrep-agent-2B-GGUF
lightonai--- library_name: transformers base_model: openbmb/MiniCPM5-2B pipeline_tag: text-generation tags: - code - code-search - tool-use - reinforcement-learning - colgrep language: - en license: apache-2.0 --- **ColGrep-Agent-2B** is a lightweight code-localization agent designed to identify the files and line ranges relevant to a GitHub issue, bug report, feature request, or natural-language question about a repository. Given a question such as *"Where are retries configured?"* or *"Why does the export crash on empty files?"*, the agent iteratively searches the repository using ColGrep, reads candidate files through a read-only terminal, and returns the precise code locations relevant to the task.
译文排队中 · 当前显示来源原文
输入 文本→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗DenseOn
lightonai> 🎯 **TL;DR**: A 149M-parameter dense (single-vector) retrieval model achieving **56.20 nDCG@10 on BEIR**, the first sub-150M dense model to break the 56 mark, **topping all base-size dense models** and outperforming several models **4× larger**. State-of-the-art retrieval is increasingly dominated by closed models, either hidden behind APIs or trained on undisclosed data. This blocks reproducibility, prevents study of possible data leakage, and gatekeeps progress to a handful of private labs. We thus decided to gather and curate a large amount of data and explore various mixtures. We release all the data used in our explorations: - Gathered pre-training data, 1.4B query-documents pairs alongside annotations used for non-destructive filtering (structural filtering, deduplication, cross-encoder pair relevancy) - Best pre-training mixture found with already applied filters - Fine-tuning datasets with query, positive and 2048 mined documents alongside their scores for 1.88M samples. Based on our findings, we trained LateOn (multi-vector/ColBERT) and DenseOn (single vector/dense) models on a proprietary Apache 2.0-compatible training dataset and release those models as well. Both are built on the ModernBERT backbone at 149M parameters, a size we believe sits at the sweet spot: large enough to handle real-world queries and documents, small enough to serve at high throughput in latency-sensitive production systems. For more information, please read our blogpost.
译文排队中 · 当前显示来源原文
输入 文本→ 输出 向量
价格待核验多模态与渠道费用须分别核对
查看详情 ↗DSE_Qwen_2.5_SOTA
lightonai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。
基础资料已收录 · 缺失资料后续补充
输入 待核验→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗GTE-ModernColBERT-v1
lightonai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。
输入 文本→ 输出 向量
价格待核验多模态与渠道费用须分别核对
查看详情 ↗LateOn
lightonai📚 Collection | 📝 Blog State-of-the-art retrieval is increasingly dominated by closed models, either hidden behind APIs or trained on undisclosed data. This blocks reproducibility, prevents study of possible data leakage, and gatekeeps progress to a handful of private labs. We thus decided to gather and curate a large amount of data and explore various mixtures. We release all the data used in our explorations: - Gathered pre-training data, 1.4B query-documents pairs alongside annotations used for non-destructive filtering (structural filtering, deduplication, cross-encoder pair relevancy) - Best pre-training mixture found with already applied filters - Fine-tuning datasets with query, positive and 2048 mined documents alongside their scores for 1.88M samples. Based on our findings, we trained LateOn (multi-vector/ColBERT) and DenseOn (single vector/dense) models on a proprietary Apache 2.0-compatible training dataset and release those models as well. Both are built on the ModernBERT backbone at 149M parameters, a size we believe sits at the sweet spot: large enough to handle real-world queries and documents, small enough to serve at high throughput in latency-sensitive production systems. For more information, please read our blogpost.
译文排队中 · 当前显示来源原文
输入 文本→ 输出 向量
价格待核验多模态与渠道费用须分别核对
查看详情 ↗LateOn-Code
lightonai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。
基础资料已收录 · 缺失资料后续补充
输入 文本→ 输出 向量
价格待核验多模态与渠道费用须分别核对
查看详情 ↗LateOn-Code-edge
lightonaiThe LateOn-Code collection is composed of PyLate models optimized for code retrieval. These late interaction models are first pre-trained following the methodology of CoRNStack. These pre-trained models are then further fine-tuned on train sets of CoIR using the nv-retriever methodology to mine hard negatives while preventing false negatives. We started from the two best ColBERT models on the BEIR benchmark for their respective sizes. The first one, LateOn-Code is based on in-house LateOn model, a new version of GTE-ModernColBERT-v1 built on ModernBERT-base (also developed at LightOn). This version underwent significantly deeper training, crossing the 57 mark on BEIR, almost a 2.5-point improvement and is thus SOTA by a large margin. We'll release this base model along with training data and boilerplates in the near future, so stay tuned\! The second, LateOn-Code-edge is a smaller model based on the edge-colbert model family from mixedbread, using the smallest variant (Ettin-17M) for maximum efficiency. For more details on the training setup, please refer to our blogpost. The original CoRNStack data in a format compatible with PyLate can be found here while the fine-tuning data can be found here. Training boilerplates can be found here in the PyLate repository
译文排队中 · 当前显示来源原文
输入 文本→ 输出 向量
价格待核验多模态与渠道费用须分别核对
查看详情 ↗LateOn-unsupervised
lightonai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。
基础资料已收录 · 缺失资料后续补充
输入 文本→ 输出 向量
价格待核验多模态与渠道费用须分别核对
查看详情 ↗LightOn-rerank-LW-2B
lightonai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。
基础资料已收录 · 缺失资料后续补充
输入 文本 · 图像→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗LightOn-rerank-LW-4B
lightonai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。
基础资料已收录 · 缺失资料后续补充
输入 文本 · 图像→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗LightOn-rerank-PW-2B
lightonai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。
基础资料已收录 · 缺失资料后续补充
输入 文本 · 图像→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗LightOn-rerank-PW-4B
lightonai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。
基础资料已收录 · 缺失资料后续补充
输入 文本 · 图像→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗LightOnOCR-0.9B-16k-1025
lightonai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。
基础资料已收录 · 缺失资料后续补充
输入 待核验→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗LightOnOCR-0.9B-32k-1025
lightonai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。
基础资料已收录 · 缺失资料后续补充
输入 待核验→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗LightOnOCR-1B-1025
lightonai> [!NOTE] > 🚀 **LightOnOCR-2 is now available and state-of-the-art on OlmOCR-bench**, with new image detection variants! > Check it out here: **lightonai/LightOnOCR-2-1B** Full BF16 version of the model. We recommend this variant for inference and further fine-tuning. **LightOnOCR-1B** is a compact, end-to-end vision–language model for Optical Character Recognition (OCR) and document understanding. It achieves state-of-the-art accuracy in its weight class while being several times faster and cheaper than larger general-purpose VLMs.
译文排队中 · 当前显示来源原文
输入 图像→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗LightOnOCR-2-1B
lightonai📄 Paper | 📝 Blog | 🚀 Demo | 📊 Dataset | 📓 Finetuning **Best OCR model .** LightOnOCR-2-1B is **LightOn's** flagship OCR model, refined with RLVR training for maximum accuracy. We recommend this variant for most OCR tasks. LightOnOCR-2 is an efficient end-to-end 1B-parameter vision-language model for converting documents (PDFs, scans, images) into clean, naturally ordered text without relying on brittle pipelines. This second version is trained on a larger and higher-quality corpus with stronger French, arXiv, and scan coverage, improved LaTeX handling, and cleaner normalization. LightOnOCR-2 achieves state-of-the-art performance on OlmOCR-Bench while being ~9× smaller and significantly faster than competing approaches.
译文排队中 · 当前显示来源原文
输入 文本 · 图像→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗LightOnOCR-2-1B-base
lightonai**Base model for fine-tuning.** This is the pre-RLVR checkpoint with strong OCR capabilities, ideal as a starting point for domain adaptation and custom fine-tuning. LightOnOCR-2 is an efficient end-to-end 1B-parameter vision-language model for converting documents (PDFs, scans, images) into clean, naturally ordered text without relying on brittle pipelines. This second version is trained on a larger and higher-quality corpus with stronger French, arXiv, and scan coverage, improved LaTeX handling, and cleaner normalization. LightOnOCR-2 achieves state-of-the-art performance on OlmOCR-Bench while being ~9× smaller and significantly faster than competing approaches.
译文排队中 · 当前显示来源原文
输入 文本 · 图像→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗LightOnOCR-2-1B-bbox
lightonai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。
基础资料已收录 · 缺失资料后续补充
输入 文本 · 图像→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗LightOnOCR-2-1B-bbox-soup
lightonai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。
输入 文本 · 图像→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗暂未找到匹配模型
可以调整厂商、分类或输入输出条件；新模型正持续收录。
COST EXPLORER
好模型，也要算好成本。
调整月度 Token 用量，直观比较不同模型的预估 API 开支。
1 M = 100 万 Token · 美元计价
仅比较同一渠道的基础文本 Token 报价
仅比较同一渠道的基础文本 Token 报价
使用已采集且单位可比的 USD / 百万 Token 渠道报价。报价为采集时快照；不计缓存优惠、阶梯价、推理额外输出与税费，请以来源的当前报价为准。
MODEL HANDBOOK
读懂模型，再做选择
API 价格应该怎么比较？+
先区分输入、输出和缓存价格，再使用同一任务和用量估算总费用。图像、音频和视频可能按张、时长或分辨率计费，不能直接与 Token 单价比较。
开放权重，就代表可以免费商用吗？+
不一定。必须逐一核对具体模型版本的许可证、商用限制及使用政策。自己部署还需要考虑显存、推理资源和运维费用。
排行榜第一，就是最适合我的模型吗？+
榜单取决于测试任务、版本与评测方法。建议用实际业务样本比较准确性、时延、稳定性和成本，再选择模型。