AI 模型库

共 个模型
下载量 收藏数 最新

Mistral-7B-Instruct-v0.2

text-generation
mistralai · mistralai/Mistral-7B-Instruct-v0.2

使用 `mistral_common` 进行编码和解码 ```py from mistral_common.tokens.tokenizers.mistral import MistralTokenizer from mistral_common.protocol.instruct.messages import UserMessage from mistral_comm

3,057,726 3133

Kronos-Tokenizer-base

time-series-forecasting
NeoQuasar · NeoQuasar/Kronos-Tokenizer-base

Kronos: A Foundation Model for the Language of Financial Markets

3,001,798 51

distilgpt2

text-generation
distilbert · distilbert/distilgpt2

DistilGPT2（Distilled-GPT2的简称）是一个在生成式预训练Transformer 2（GPT-2）最小版本监督下预训练的英语语言模型。与GPT-2类似，DistilGPT2可用于文本生成。本模型卡的用户还应考虑关于设计的相关信息

3,000,562 629

sam3

mask-generation
facebook · facebook/sam3

mask-generation

2,999,373 1973

tiny-random-LlamaForCausalLM

text-generation
hmellor · hmellor/tiny-random-LlamaForCausalLM

<!-- Provide a quick summary of what the model is/does. -->

2,988,632 0

all-MiniLM-L12-v2

sentence-similarity
sentence-transformers · sentence-transformers/all-MiniLM-L12-v2

all-MiniLM-L12-v2 这是一个sentence-transformers模型：它将句子和段落映射到384维的稠密向量空间，可用于聚类或语义搜索等任务。

2,985,710 308

Qwen3.5-0.8B

image-text-to-text
Qwen · Qwen/Qwen3.5-0.8B

> [!Note] > This repository contains model weights and configuration files for the post-trained model in the Hugging Face Transformers format. > > These artifacts are compatible with Hugging Face Tra

2,974,591 530

TinyLlama-1.1B-Chat-v1.0

text-generation
TinyLlama · TinyLlama/TinyLlama-1.1B-Chat-v1.0

TinyLlama项目旨在**在3万亿个token上预训练一个11亿参数的Llama模型**。通过适当的优化，我们仅需使用16块A100-40G GPU，就能在"短短"90天内完成这一目标🚀🚀。训练已于2023年9月1日开始。

2,953,734 1580

finance-embeddings-investopedia

sentence-similarity
FinLang · FinLang/finance-embeddings-investopedia

这是FinLang团队为金融应用开发的Investopedia嵌入模型。该模型使用我们开源的金融数据集进行训练，数据集来自https://huggingface.co/datasets/FinLang/investopedia-embedding-dataset

2,937,393 64

bart-large-mnli

zero-shot-classification
facebook · facebook/bart-large-mnli

This is the checkpoint for bart-large after being trained on the MultiNLI (MNLI) dataset.

2,925,365 1567

bert-tiny

prajjwal1 · prajjwal1/bert-tiny

以下模型是从官方Google BERT仓库中的Tensorflow检查点转换而来的Pytorch预训练模型。

2,922,256 145

mobilebert-uncased

google · google/mobilebert-uncased

MobileBERT：面向资源受限设备的紧凑型任务无关BERT

2,921,185 71

ms-marco-MiniLM-L12-v2

text-ranking
cross-encoder · cross-encoder/ms-marco-MiniLM-L12-v2

该模型在MS Marco段落排序任务上进行了训练。

2,920,008 105

dinov2-large

image-feature-extraction
facebook · facebook/dinov2-large

Vision Transformer (large-sized model) trained using DINOv2

2,879,874 108

fashion-clip

zero-shot-image-classification
patrickjohncyh · patrickjohncyh/fashion-clip

Disclaimer: The model card adapts the model card from here.

2,874,693 280

speaker-diarization-community-1

automatic-speech-recognition
pyannote · pyannote/speaker-diarization-community-1

自动语音识别

2,856,155 361

llava-1.5-7b-hf

image-text-to-text
llava-hf · llava-hf/llava-1.5-7b-hf

以下是Llava 7b模型的模型卡，该内容复制自原始Llava模型卡，您可在此处找到。

2,848,725 359

faster-whisper-tiny-int8

rhasspy · rhasspy/faster-whisper-tiny-int8
2,838,165 5

DeepSeek-OCR

image-text-to-text
deepseek-ai · deepseek-ai/DeepSeek-OCR

🌟 Github | 📥 Model Download | 📄 Paper Link | 📄 Arxiv Paper Link |

2,824,757 3227

t5-small

translation
google-t5 · google-t5/t5-small

1. 模型详情 2. 用途 3. 偏见、风险与局限性 4. 训练详情 5. 评估 6. 环境影响 7. 引用 8. 模型卡片作者 9. 如何开始使用该模型

2,782,668 544
1 ... 4 5 6 7 8 9 10