Fingumv3

🚀 基于 dunzhang/stella_en_1.5B_v5 的句子转换器

这是一个基于 dunzhang/stella_en_1.5B_v5 微调的 句子转换器 模型。它可以将句子和段落映射到一个 1024 维的密集向量空间，可用于语义文本相似度计算、语义搜索、释义挖掘、文本分类、聚类等任务。

🚀 快速开始

直接使用（句子转换器）

首先安装句子转换器库：

pip install -U sentence-transformers

然后你可以加载这个模型并进行推理。

from sentence_transformers import SentenceTransformer

# 从 🤗 Hub 下载
model = SentenceTransformer("sentence_transformers_model_id")
# 运行推理
sentences = [
    'The Tchaikovsky Symphony Orchestra is a Russian classical music orchestra established in 1930. It was founded as the Moscow Radio Symphony Orchestra, and served as the official symphony for the Soviet All-Union Radio network. Following the dissolution of the, Soviet Union in 1991, the orchestra was renamed in 1993 by the Russian Ministry of Culture in recognition of the central role the music of Tchaikovsky plays in its repertoire. The current music director is Vladimir Fedoseyev, who has been in that position since 1974.',
    'Instruct: Given a web search query, retrieve relevant passages that answer the query.\nQuery: Tchaikovsky Symphony Orchestra',
    'Instruct: Given a web search query, retrieve relevant passages that answer the query.\nQuery: Sierra del Lacandón',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 1024]

# 获取嵌入向量的相似度得分
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]

✨ 主要特性

该模型具有以下特点：

• 基于 dunzhang/stella_en_1.5B_v5 进行微调。
• 能够将句子和段落映射到 1024 维的密集向量空间。
• 可用于多种自然语言处理任务，如语义文本相似度计算、语义搜索等。

📦 安装指南

若要使用该模型，需先安装 sentence-transformers 库：

pip install -U sentence-transformers

💻 使用示例

基础用法

from sentence_transformers import SentenceTransformer

# 从 🤗 Hub 下载
model = SentenceTransformer("sentence_transformers_model_id")
# 运行推理
sentences = [
    'The Tchaikovsky Symphony Orchestra is a Russian classical music orchestra established in 1930. It was founded as the Moscow Radio Symphony Orchestra, and served as the official symphony for the Soviet All-Union Radio network. Following the dissolution of the, Soviet Union in 1991, the orchestra was renamed in 1993 by the Russian Ministry of Culture in recognition of the central role the music of Tchaikovsky plays in its repertoire. The current music director is Vladimir Fedoseyev, who has been in that position since 1974.',
    'Instruct: Given a web search query, retrieve relevant passages that answer the query.\nQuery: Tchaikovsky Symphony Orchestra',
    'Instruct: Given a web search query, retrieve relevant passages that answer the query.\nQuery: Sierra del Lacandón',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 1024]

# 获取嵌入向量的相似度得分
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]

📚 详细文档

模型详情

模型描述

模型来源

• 文档：句子转换器文档
• 仓库：GitHub 上的句子转换器
• Hugging Face：Hugging Face 上的句子转换器

完整模型架构

SentenceTransformer(
  (0): Transformer({'max_seq_length': 8096, 'do_lower_case': False}) with Transformer model: Qwen2Model 
  (1): Pooling({'word_embedding_dimension': 1536, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
  (2): Dense({'in_features': 1536, 'out_features': 1024, 'bias': True, 'activation_function': 'torch.nn.modules.linear.Identity'})
)

评估

信息检索

使用 InformationRetrievalEvaluator 进行评估。

训练详情

训练超参数

非默认超参数

• eval_strategy: steps
• per_device_eval_batch_size: 4
• gradient_accumulation_steps: 4
• learning_rate: 2e-05
• max_steps: 1500
• lr_scheduler_type: cosine
• warmup_ratio: 0.1
• warmup_steps: 5
• bf16: True
• tf32: True
• optim: adamw_torch_fused
• gradient_checkpointing: True
• gradient_checkpointing_kwargs: {'use_reentrant': False}
• batch_sampler: no_duplicates

所有超参数

训练日志

框架版本

• Python: 3.10.12
• 句子转换器: 3.0.1
• Transformers: 4.41.2
• PyTorch: 2.2.0+cu121
• Accelerate: 0.33.0
• Datasets: 2.20.0
• Tokenizers: 0.19.1

🔧 技术细节

该模型基于 dunzhang/stella_en_1.5B_v5 进行微调，使用了 SentenceTransformer 架构。在训练过程中，采用了多种超参数进行优化，如学习率、批量大小等。同时，使用了 MatryoshkaLoss 和 MultipleNegativesRankingLoss 作为损失函数。

📄 许可证

文档中未提及相关许可证信息。

📖 引用

BibTeX

句子转换器

@inproceedings{reimers-2019-sentence-bert,
    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
    author = "Reimers, Nils and Gurevych, Iryna",
    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
    month = "11",
    year = "2019",
    publisher = "Association for Computational Linguistics",
    url = "https://arxiv.org/abs/1908.10084",
}

MatryoshkaLoss

@misc{kusupati2024matryoshka,
    title={Matryoshka Representation Learning}, 
    author={Aditya Kusupati and Gantavya Bhatt and Aniket Rege and Matthew Wallingford and Aditya Sinha and Vivek Ramanujan and William Howard-Snyder and Kaifeng Chen and Sham Kakade and Prateek Jain and Ali Farhadi},
    year={2024},
    eprint={2205.13147},
    archivePrefix={arXiv},
    primaryClass={cs.LG}
}

MultipleNegativesRankingLoss

@misc{henderson2017efficient,
    title={Efficient Natural Language Response Suggestion for Smart Reply}, 
    author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
    year={2017},
    eprint={1705.00652},
    archivePrefix={arXiv},
    primaryClass={cs.CL}
}