AI NEWS · 模型情报站发现能力边界,让每一次选择更有依据 ↗基础档案先收录 · 缺失资料持续补齐
THE AI MODEL DIRECTORY 模型探索,从这里开始

找到适合你的 AI 模型。

从语言到影像,从开源到 API。读懂模型能力、比较真实成本,
为你的下一个想法,找到合适的智能引擎。

热门探索
84,999 款模型档案13202 家厂商 / 发布者45 个能力分类465 款有可比报价 · 30 款有公开评测
T文本生成▧图像生成▷视频生成⌘代码生成◖语音合成♫音乐生成⬡3D 建模▤文档分析
DISCOVER & COMPARE

探索 AI 模型 2428

为你发现值得关注的模型

EttinX-sts-xxs

dleemiller

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 ↗
来源 / 文档 ↗

**ner-legal-bert-base-cased-ptbr** is a NER model (token classification) in the legal domain in Portuguese that was finetuned from the model dominguesm/legal-bert-base-cased-ptbr by using a NER objective. The model is intended to assist NLP research in the legal field, computer law and legal technology applications. Several legal texts in Portuguese (more information below) were used with the following labels: The labels were inspired by the LeNER_br dataset.

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 ↗
来源 / 文档 ↗

ko-reranker

Dongjin-kr

ko-reranker는 BAAI/bge-reranker-larger 기반 한국어 데이터에 대한 fine-tuned model 입니다. 보다 자세한 사항은 korean-reranker-git / AWS Blog, 한국어 Reranker를 활용한 검색 증강 생성(RAG) 성능 올리기을 참고하세요 - #### Reranker는 임베딩 모델과 달리 질문과 문서를 입력으로 사용하며 임베딩 대신 유사도를 직접 출력합니다. - #### Reranker에 질문과 구절을 입력하면 연관성 점수를 얻을 수 있습니다. - #### Reranker는 CrossEntropy loss를 기반으로 최적화되므로 관련성 점수가 특정 범위에 국한되지 않습니다. - #### **컨택스트 순서가 정확도에 영향 준다**(Lost in Middle, *Liu et al., 2023*)

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 ↗
来源 / 文档 ↗

THX-01

doofz

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 ↗
来源 / 文档 ↗

vibert-capu

dragonSwing

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 ↗
来源 / 文档 ↗

If my open source models have been useful to you, please consider supporting me in building small, useful AI models for everyone (and help me afford med school / help out my parents financially). Thanks! **bert-large-NER** is a fine-tuned BERT model that is ready to use for **Named Entity Recognition** and achieves **state-of-the-art performance** for the NER task. It has been trained to recognize four types of entities: location (LOC), organizations (ORG), person (PER) and Miscellaneous (MISC). Specifically, this model is a *bert-large-cased* model that was fine-tuned on the English version of the standard CoNLL-2003 Named Entity Recognition dataset.

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 ↗
来源 / 文档 ↗

If my open source models have been useful to you, please consider supporting me in building small, useful AI models for everyone (and help me afford med school / help out my parents financially). Thanks! **distilbert-NER** is the fine-tuned version of **DistilBERT**, which is a distilled variant of the BERT model. DistilBERT has fewer parameters than BERT, making it smaller, faster, and more efficient. distilbert-NER is specifically fine-tuned for the task of **Named Entity Recognition (NER)**. This model accurately identifies the same four types of entities as its BERT counterparts: location (LOC), organizations (ORG), person (PER), and Miscellaneous (MISC). Although it is a more compact model, distilbert-NER demonstrates a robust performance in NER tasks, balancing between size, speed, and accuracy.

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 ↗
来源 / 文档 ↗

This model is a fine-tuned version of roberta-base on the NYT News dataset, which contains 256,000 news titles from articles published from 2000 to the present (https://www.kaggle.com/datasets/aryansingh0909/nyt-articles-21m-2000-present). It achieves the following results on the test set of 51200 cases: - Accuracy: 0.91 - F1: 0.91 - Precision: 0.91 - Recall: 0.91 class |Description -|- 0 |Sports 1 |Arts, Culture, and Entertainment 2 |Business and Finance 3 |Health and Wellness 4 |Lifestyle and Fashion 5 |Science and Technology 6 |Politics 7 |Crime The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 500 - num_epochs: 5

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 ↗
来源 / 文档 ↗

bert-base-romanian-ner

dumitrescustefan

**bert-base-romanian-ner** is a fine-tuned BERT model that is ready to use for **Named Entity Recognition** and achieves **state-of-the-art performance** for the NER task. It has been trained to recognize **15** types of entities: persons, geo-political entities, locations, organizations, languages, national_religious_political entities, datetime, period, quantity, money, numeric, ordinal, facilities, works of art and events. Specifically, this model is a bert-base-romanian-cased-v1 model that was fine-tuned on RONEC version 2.0, which holds 12330 sentences with over 0.5M tokens, to a total of 80.283 distinctly annotated entities. RONECv2 is a BIO2 annotated corpus, meaning this model will generate "B-" and "I-" style labels for entities. The model will generate labels according to the following list: ['O', 'B-PERSON', 'I-PERSON', 'B-ORG', 'I-ORG', 'B-GPE', 'I-GPE', 'B-LOC', 'I-LOC', 'B-NAT_REL_POL', 'I-NAT_REL_POL', 'B-EVENT', 'I-EVENT', 'B-LANGUAGE', 'I-LANGUAGE', 'B-WORK_OF_ART', 'I-WORK_OF_ART', 'B-DATETIME', 'I-DATETIME', 'B-PERIOD', 'I-PERIOD', 'B-MONEY', 'I-MONEY', 'B-QUANTITY', 'I-QUANTITY', 'B-NUMERIC', 'I-NUMERIC', 'B-ORDINAL', 'I-ORDINAL', 'B-FACILITY', 'I-FACILITY']. Label 'O' represents Other.

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 ↗
来源 / 文档 ↗
COST EXPLORER

好模型,也要算好成本。

费用分析

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

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

选型与常见问题
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。

AI NEWS · 从信息到选择

资讯看趋势,工具提效率,模型筑可能。

探索 AI 资讯 ↗发现 AI 工具 ↗