yuan-embedding-2.0-zh-query-note

SentenceTransformer based on IEITYuan/Yuan-embedding-2.0-zh

This is a sentence-transformers model finetuned from IEITYuan/Yuan-embedding-2.0-zh. It maps sentences & paragraphs to a 1792-dimensional dense vector space and can be used for retrieval.

Model Details

Model Description

• Model Type: Sentence Transformer
• Base model: IEITYuan/Yuan-embedding-2.0-zh <!-- at revision fb4ab1ed9d3447b64c79e305c8913340327668b5 -->
• Maximum Sequence Length: 512 tokens
• Output Dimensionality: 1792 dimensions
• Similarity Function: Cosine Similarity
• Supported Modality: Text

<!-- - **Training Dataset:** Unknown --> <!-- - **Language:** Unknown --> <!-- - **License:** Unknown -->

Model Sources

• Documentation: Sentence Transformers Documentation
• Repository: Sentence Transformers on GitHub
• Hugging Face: Sentence Transformers on Hugging Face

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'transformer_task': 'feature-extraction', 'modality_config': {'text': {'method': 'forward', 'method_output_name': 'last_hidden_state'}}, 'module_output_name': 'token_embeddings', 'architecture': 'BertModel'})
  (1): Pooling({'embedding_dimension': 1024, 'pooling_mode': 'mean', 'include_prompt': True})
  (2): Dense({'in_features': 1024, 'out_features': 1792, 'bias': True, 'activation_function': 'torch.nn.modules.linear.Identity', 'module_input_name': 'sentence_embedding', 'module_output_name': 'sentence_embedding'})
)

Usage

Direct Usage (Sentence Transformers)

First install the Sentence Transformers library:

pip install -U sentence-transformers

Then you can load this model and run inference.

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("sentence_transformers_model_id")
# Run inference
queries = [
    '上学文具分享',
]
documents = [
    '准初三生的书包里有啥😉👉🏻💗\n都是一些很真实的东西哈哈哈 \n我就问有谁懂…？\n#笔袋[话题]# #笔袋介绍[话题]# #我的文具分享[话题]# \n#晒晒我的书桌[话题]# #我的日常[话题]# \n#whatsinmybag[话题]# #书包里面装什么[话题]# \n#书包[话题]# ',
    '下辈子我也要当仓鼠\n傻傻的胖胖的不知道悲伤……#珍藏的宠物照[话题]# #侏儒仓鼠[话题]# #鼠鼠教[话题]# #宠物[话题]# #宠物日常[话题]# ',
    '云南丽江～ 束河古镇风景（上）\n拍于2023年11.19哦～\n从白沙坐公交去的束河古镇\n进门的时候忘记拍牌楼了[笑哭R]\n刚进门不久走到了茶马古道博物馆但是是关闭状态的\n不走人多的地方风景很不错\n图上那只松鼠的表情真的笑死\n看起来比香格里拉和雨崩的可爱\n建议沿着水流走 风景不会太差\n#云南[话题]# #云南游[话题]# #云南丽江[话题]# #束河古镇[话题]# ',
]
query_embeddings = model.encode_query(queries)
document_embeddings = model.encode_document(documents)
print(query_embeddings.shape, document_embeddings.shape)
# [1, 1792] [3, 1792]

# Get the similarity scores for the embeddings
similarities = model.similarity(query_embeddings, document_embeddings)
print(similarities)
# tensor([[ 0.6374,  0.0472, -0.0356]])

<!-- ### Direct Usage (Transformers) <details><summary>Click to see the direct usage in Transformers</summary> </details> --> <!-- ### Downstream Usage (Sentence Transformers) You can finetune this model on your own dataset. <details><summary>Click to expand</summary> </details> --> <!-- ### Out-of-Scope Use *List how the model may foreseeably be misused and address what users ought not to do with the model.* -->

Evaluation

Metrics

Information Retrieval

• Datasets: query_note_test and query_note_val
• Evaluated with <code>InformationRetrievalEvaluator</code>

Information Retrieval

• Datasets: query_note_test_256 and query_note_val_256
• Evaluated with <code>InformationRetrievalEvaluator</code> with these parameters:

  {
      "truncate_dim": 256
  }
  

<!-- ## Bias, Risks and Limitations *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.* --> <!-- ### Recommendations *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.* -->

Training Details

Training Dataset

Unnamed Dataset

• Size: 164,633 training samples
• Columns: <code>anchor</code> and <code>positive</code>
• Approximate statistics based on the first 100 samples:

  	anchor	positive
  type	string	string
  modality	text	text
  details	<ul><li>min: 3 tokens</li><li>mean: 8.78 tokens</li><li>max: 17 tokens</li></ul>	<ul><li>min: 38 tokens</li><li>mean: 308.37 tokens</li><li>max: 512 tokens</li></ul>

• Samples:

  anchor	positive
  <code>jeep冲锋衣属于档次</code>	<code>🧥吉普冲锋衣，秋季必备🍂<br>Jeep吉普官方正品，品质有保障👍。 <br> <br>卡其色/M码，适合90-110斤，款式时尚百搭。 <br> <br>防风防水设计，适合户外活动，保暖又舒适😊。 <br> <br>秋季穿搭必备，你值得拥有！ #小红书秋日焕新[话题]# #jeep[话题]# #冲锋衣[话题]# #秋季外套[话题]# #正品保证[话题]# #防风防水[话题]# #户外穿搭[话题]# #时尚百搭[话题]# #品质选择[话题]#</code>
  <code>喝酒文案微醺</code>	<code>秋冬时刻需要威士忌 | 见面吗？！<br>🍽️<br>属于我和先生的浪漫约会日常<br>便是放下孩子后的小酌怡情~<br> 刚好最近气温骤降，多了些凉意<br>想来一杯Whisky的心情达到上限<br> 🍽️<br>听闻格兰菲迪最近和MU·慕有出合作套餐<br>与先生的couple vacation时刻瞬间启动~<br>在轻奢环境下更适合开一瓶格兰菲迪22年单一麦芽苏格兰威士忌<br>@格兰菲迪 Glenfiddich <br>作为在全球屡获殊荣的单一麦芽苏格兰威士忌品牌<br>自诞生起就从未停止探索的脚步<br>不断探究威士忌与餐食搭配的新风味<br> 🍽️<br>当杯中深红琥珀色的酒体<br>在灯光下衬得更加迷人时<br>黑巧克力以及葡萄果干的浓郁香气也同时散发<br>象拔蚌和波士顿龙虾的上场<br>将视觉的色与口感的香瞬间突出<br>薄如刀片的爽脆蚌肉和Q弹龙虾肉<br>在酒精的碰撞下太立体太美好<br> <br>余韵的温润柑橘果香和馥郁水果蛋糕香<br>像是激情生活之后的源远流长<br>搭配新西兰羊排嫩多汁的奶香气息<br>像是被酒精注入新的灵感和层次<br> 🤎<br>婚后的微醺节奏<br>同样能拉近彼此的距离<br>大家也可以打卡格兰菲迪合作餐厅哦<br>用一杯格兰菲迪杯找寻浪漫~找寻生活吧<br>#广州探店[话题]# #福鹿结伴山海寻鲜[话题]# #威士忌推荐[话题]# #格兰菲迪[话题]# #格兰菲迪单一麦芽威士忌[话题]#</code>
  <code>长沙酒吧</code>	<code>长沙一定要去的6️⃣大夜店！！！<br>长沙夜生活 蹦迪💃酒吧 再多的攻略都不及去亲身体验一次！！<br> <br>✅长沙一定要去的夜店❗️❗️<br>1️⃣X-sta：长沙最火爆的高空edm场 声光电体验感强 非常具有科技感 总投资1.8亿[赞R] 四五六楼是包厢 娱乐综合体<br>2️⃣one9：小厅bounce场 韩国江南风夜店 前身是火爆长沙的NBEK 喜欢小厅的朋友不要错过啦[派对R]<br>3️⃣FTF：新开业中型edm/bounce酒吧 位置在海信广场 以前的超级猴子[派对R]<br>4️⃣kok：网红爆品小厅 每晚都有男团演出与玩家们互动 人气也一直居高不下[自拍R]<br>5️⃣猩猩地堡：连锁品牌 打卡的人很多 长沙年轻人的聚集地<br>6️⃣试音：长沙hiphop吧天花板 嘉宾众多气氛火爆 值得打卡<br> <br>🌿住宿推荐<br>建议住五一广场/开福区万达广场（去哪都方便）<br> <br>⚠️温馨提示：想去长沙夜店玩的朋友记得提前做好攻略，提前找销售预约好门店避免排队！<br> <br>希望这些对您有所帮助！<br>图片来源于网络 侵删！<br>#长沙酒吧[话题]# #长沙酒吧推荐[话题]# #长沙酒吧订台[话题]# #长沙旅游[话题]# #长沙蹦迪[话题]#</code>

• Loss: <code>MatryoshkaLoss</code> with these parameters:

  {
      "loss": "MultipleNegativesRankingLoss",
      "matryoshka_dims": [
          1024,
          256
      ],
      "matryoshka_weights": [
          1,
          1
      ],
      "n_dims_per_step": -1
  }
  

Training Hyperparameters

Non-Default Hyperparameters

• per_device_train_batch_size: 256
• learning_rate: 0.0001
• weight_decay: 0.01
• num_train_epochs: 1
• lr_scheduler_type: cosine
• warmup_ratio: 0.05
• seed: 3407
• bf16: True
• batch_sampler: no_duplicates

All Hyperparameters

<details><summary>Click to expand</summary>

• overwrite_output_dir: False
• do_predict: False
• prediction_loss_only: True
• per_device_train_batch_size: 256
• per_device_eval_batch_size: 8
• per_gpu_train_batch_size: None
• per_gpu_eval_batch_size: None
• gradient_accumulation_steps: 1
• eval_accumulation_steps: None
• torch_empty_cache_steps: None
• learning_rate: 0.0001
• weight_decay: 0.01
• adam_beta1: 0.9
• adam_beta2: 0.999
• adam_epsilon: 1e-08
• max_grad_norm: 1.0
• num_train_epochs: 1
• max_steps: -1
• lr_scheduler_type: cosine
• lr_scheduler_kwargs: {}
• warmup_ratio: 0.05
• warmup_steps: 0
• log_level: passive
• log_level_replica: warning
• log_on_each_node: True
• logging_nan_inf_filter: True
• save_safetensors: True
• save_on_each_node: False
• save_only_model: False
• restore_callback_states_from_checkpoint: False
• no_cuda: False
• use_cpu: False
• use_mps_device: False
• seed: 3407
• data_seed: None
• jit_mode_eval: False
• use_ipex: False
• bf16: True
• fp16: False
• fp16_opt_level: O1
• half_precision_backend: auto
• bf16_full_eval: False
• fp16_full_eval: False
• tf32: None
• local_rank: 0
• ddp_backend: None
• tpu_num_cores: None
• tpu_metrics_debug: False
• debug: []
• dataloader_drop_last: False
• dataloader_num_workers: 0
• dataloader_prefetch_factor: None
• past_index: -1
• disable_tqdm: False
• remove_unused_columns: True
• label_names: None
• load_best_model_at_end: False
• ignore_data_skip: False
• fsdp: []
• fsdp_min_num_params: 0
• fsdp_config: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
• fsdp_transformer_layer_cls_to_wrap: None
• accelerator_config: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
• parallelism_config: None
• deepspeed: None
• label_smoothing_factor: 0.0
• optim: adamw_torch_fused
• optim_args: None
• adafactor: False
• group_by_length: False
• length_column_name: length
• ddp_find_unused_parameters: None
• ddp_bucket_cap_mb: None
• ddp_broadcast_buffers: False
• dataloader_pin_memory: True
• dataloader_persistent_workers: False
• skip_memory_metrics: True
• use_legacy_prediction_loop: False
• push_to_hub: False
• resume_from_checkpoint: None
• hub_model_id: None
• hub_strategy: every_save
• hub_private_repo: None
• hub_always_push: False
• hub_revision: None
• gradient_checkpointing: False
• gradient_checkpointing_kwargs: None
• include_inputs_for_metrics: False
• include_for_metrics: []
• eval_do_concat_batches: True
• fp16_backend: auto
• push_to_hub_model_id: None
• push_to_hub_organization: None
• mp_parameters:
• auto_find_batch_size: False
• full_determinism: False
• torchdynamo: None
• ray_scope: last
• ddp_timeout: 1800
• torch_compile: False
• torch_compile_backend: None
• torch_compile_mode: None
• include_tokens_per_second: False
• include_num_input_tokens_seen: False
• neftune_noise_alpha: None
• optim_target_modules: None
• batch_eval_metrics: False
• eval_on_start: False
• use_liger_kernel: False
• liger_kernel_config: None
• eval_use_gather_object: False
• average_tokens_across_devices: False
• prompts: None
• batch_sampler: no_duplicates
• multi_dataset_batch_sampler: proportional
• router_mapping: {}
• learning_rate_mapping: {}

</details>

Training Logs

Training Time

• Training: 54.3 minutes

Framework Versions

• Python: 3.12.3
• Sentence Transformers: 5.5.1
• Transformers: 4.56.2
• PyTorch: 2.11.0+cu128
• Accelerate: 1.13.0
• Datasets: 4.3.0
• Tokenizers: 0.22.2

Citation

BibTeX

Sentence Transformers

@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{oord2019representationlearningcontrastivepredictive,
      title={Representation Learning with Contrastive Predictive Coding},
      author={Aaron van den Oord and Yazhe Li and Oriol Vinyals},
      year={2019},
      eprint={1807.03748},
      archivePrefix={arXiv},
      primaryClass={cs.LG},
      url={https://arxiv.org/abs/1807.03748},
}

<!-- ## Glossary *Clearly define terms in order to be accessible across audiences.* --> <!-- ## Model Card Authors *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.* --> <!-- ## Model Card Contact *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.* -->