README.md

metadata

base_model: BAAI/bge-small-en-v1.5
datasets: []
language: []
library_name: sentence-transformers
pipeline_tag: sentence-similarity
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:1500
  - loss:BatchAllTripletLoss
widget:
  - source_sentence: 实现一段代码，将给定短语中的每个单词按字母顺序排列，然后按照每个单词首字母的字典顺序对这些单词进行排序，并保留每个单词中字符的原始顺序。
    sentences:
      - 可以给出小猫、小狗和小兔的年龄对温度的适应度和健康的影响的代码吗？
      - 绘制一个5x5的矩阵，矩阵中的单元格颜色交替，模式如下所描述（黑=实心块，白=空白块）：
      - >-
        Write a Java program that simulates a basic text-based RPG (Role-Playing
        Game) with the following features:
           - Character creation: allow the user to choose a name, class, and starting attributes.
           - Combat system: implement turn-based combat against randomly generated enemies.
           - Leveling up: increase character attributes based on experience points gained from defeating enemies.
           - Inventory system: collect items dropped by defeated enemies and manage them in an inventory menu.
         
  - source_sentence: >-
      Create a HTML page with an ordered list of items using Five items: apple,
      banana, orange, strawberry, and lemon.
    sentences:
      - >-
        How can we modify the given Ruby code to determine if a candidate
        fulfills all the eligibility criteria for the US presidency?
        Specifically, in addition to the age requirement of 35 years, we also
        need to check if the candidate is a natural-born citizen and has been a
        resident of the United States for at least 14 years. Can you suggest a
        more optimized code to accomplish this task? 
      - 从系统生物学的视角解读生物科技的重要性。
      - 为一家以室内植物为主的植物店计划一场营销活动。
  - source_sentence: 请使用尽可能简单的语言解释主体-客体模型（Subject-Object Model）。
    sentences:
      - 'Generate an algorithm for the game Hangman. '
      - 如何使用 JavaScript 将两个 HTML 元素互换位置？
      - >-
        In Swift, what function can I use to shorten the sentence "I'm feeling
        kind of tired after having worked all day" while maintaining the same
        meaning and tone? Can you provide an example of the shortened sentence
        using the function? 
  - source_sentence: 在一个Dockerfile中，何时使用ADD指令与COPY指令？
    sentences:
      - 在给定的数列中寻找子数组，使其元素和最大。
      - >-
        In an Excel spreadsheet that contains information about employees, there
        is a column for job titles. John's job title is listed as "Manager." Add
        a description of John's responsibilities to the sentence "John was a"
        using an Excel formula. 
      - >-
        多项式p(z) = z^3 + Az^2 + Bz +
        C为复数系数多项式。如果我们知道A、B、C为实数，而p根存在两个复数根r1和r2，第三个根也是它们的共轭复数r3。证明虚部非零。
  - source_sentence: 解析三种大数据分析工具，请包括使用案例。
    sentences:
      - >-
        How can the traveler determine the correct number of open hands after
        the 2021st gesture based on the pattern provided by the villagers? 

        Here is a possible solution in Ruby:

        open_hands = 1

        closed_hands = 1

        (1..2021).each do |i|
          if i % 2 == 1
            closed_hands += open_hands
            open_hands = closed_hands - open_hands
          else
            open_hands += closed_hands
            closed_hands = open_hands - closed_hands
          end
        end

        puts "After the 2021st gesture, the number of open hands is
        #{open_hands}." 

        Can you explain how this Ruby code works to solve the puzzle posed by
        the villagers? 
      - >-
        How can I use C# code to simulate the discovery of a rare and valuable
        book collection secretly housed in a local library, and then capture the
        town's reaction to the discovery? 
      - >-
        How can I create a stylish outfit that incorporates intricate embroidery
        patterns and luxurious fabric, while also being budget-friendly? Can you
        provide a creative solution using Ruby code that balances affordability
        and elegance?

        For example, you could use the following code to search for affordable
        fabric options and embroidery patterns:

        ```ruby

        require 'etsy'

        # Search for affordable fabrics on Etsy

        results = Etsy::Search.new('affordable fabric', :includes => [:Images],
        :price_max => 50).results

        # Search for intricate embroidery patterns on Etsy

        embroidery_results = Etsy::Search.new('intricate embroidery pattern',
        :includes => [:Images], :price_max => 100).results

        # Choose a fabric and embroidery pattern to use in the outfit

        chosen_fabric = results.sample

        chosen_embroidery = embroidery_results.sample

        # Use the chosen fabric and embroidery pattern to create a stylish
        outfit

        # ...

        ```

        Can you provide additional code and reasoning to complete the solution? 

SentenceTransformer based on BAAI/bge-small-en-v1.5

This is a sentence-transformers model finetuned from BAAI/bge-small-en-v1.5. It maps sentences & paragraphs to a 384-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.

Model Details

Model Description

• Model Type: Sentence Transformer
• Base model: BAAI/bge-small-en-v1.5
• Maximum Sequence Length: 512 tokens
• Output Dimensionality: 384 tokens
• Similarity Function: Cosine Similarity

Model Sources

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

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 512, 'do_lower_case': True}) with Transformer model: BertModel 
  (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, '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): Normalize()
)

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("Snivellus789/router-embedding-tuned-2")
# Run inference
sentences = [
    '解析三种大数据分析工具，请包括使用案例。',
    "How can I create a stylish outfit that incorporates intricate embroidery patterns and luxurious fabric, while also being budget-friendly? Can you provide a creative solution using Ruby code that balances affordability and elegance?\nFor example, you could use the following code to search for affordable fabric options and embroidery patterns:\n```ruby\nrequire 'etsy'\n# Search for affordable fabrics on Etsy\nresults = Etsy::Search.new('affordable fabric', :includes => [:Images], :price_max => 50).results\n# Search for intricate embroidery patterns on Etsy\nembroidery_results = Etsy::Search.new('intricate embroidery pattern', :includes => [:Images], :price_max => 100).results\n# Choose a fabric and embroidery pattern to use in the outfit\nchosen_fabric = results.sample\nchosen_embroidery = embroidery_results.sample\n# Use the chosen fabric and embroidery pattern to create a stylish outfit\n# ...\n```\nCan you provide additional code and reasoning to complete the solution? ",
    "How can I use C# code to simulate the discovery of a rare and valuable book collection secretly housed in a local library, and then capture the town's reaction to the discovery? ",
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 384]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]

Training Details

Training Dataset

Unnamed Dataset

• Size: 1,500 training samples
• Columns: sentence and label
• Approximate statistics based on the first 1000 samples:

  	sentence	label
  type	string	int
  details	min: 8 tokens mean: 95.61 tokens max: 512 tokens	0: ~50.00% 1: ~50.00%

• Samples:

  sentence	label
  请输出所有跟政企市场相关的关键词列表	0
  开发一个定制的JavaScript解决方案，用于有效地平衡和排序一个二叉树。你可以假设输入是一个平衡因子擯至2的大O()为Log(N)的AVL树。专注于实现自我调整二叉搜索树的变换，当面对不平衡操作时，如插入或删除节点。确保你的解决方案为潜在的边缘案例做好准备，并具有健壮的错误处理策略。你的代码应该清晰地记录和优化效率。	0
  在一个尚未被公开的领域中，描述五个最具创新性的产品概念。	0

• Loss: BatchAllTripletLoss

Training Hyperparameters

Non-Default Hyperparameters

• per_device_train_batch_size: 16
• per_device_eval_batch_size: 16
• learning_rate: 2e-05
• num_train_epochs: 2
• warmup_ratio: 0.1
• bf16: True
• batch_sampler: no_duplicates

All Hyperparameters

Click to expand

• overwrite_output_dir: False
• do_predict: False
• eval_strategy: no
• prediction_loss_only: True
• per_device_train_batch_size: 16
• per_device_eval_batch_size: 16
• per_gpu_train_batch_size: None
• per_gpu_eval_batch_size: None
• gradient_accumulation_steps: 1
• eval_accumulation_steps: None
• learning_rate: 2e-05
• weight_decay: 0.0
• adam_beta1: 0.9
• adam_beta2: 0.999
• adam_epsilon: 1e-08
• max_grad_norm: 1.0
• num_train_epochs: 2
• max_steps: -1
• lr_scheduler_type: linear
• lr_scheduler_kwargs: {}
• warmup_ratio: 0.1
• 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: 42
• 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}
• deepspeed: None
• label_smoothing_factor: 0.0
• optim: adamw_torch
• 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: False
• hub_always_push: False
• gradient_checkpointing: False
• gradient_checkpointing_kwargs: None
• include_inputs_for_metrics: False
• 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
• dispatch_batches: None
• split_batches: 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
• batch_sampler: no_duplicates
• multi_dataset_batch_sampler: proportional

Training Logs

Epoch	Step	Training Loss
1.0638	100	0.097

Framework Versions

• Python: 3.10.12
• Sentence Transformers: 3.0.1
• Transformers: 4.42.4
• PyTorch: 2.3.1+cu121
• Accelerate: 0.33.0.dev0
• Datasets: 2.20.0
• Tokenizers: 0.19.1

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",
}

BatchAllTripletLoss

@misc{hermans2017defense,
    title={In Defense of the Triplet Loss for Person Re-Identification}, 
    author={Alexander Hermans and Lucas Beyer and Bastian Leibe},
    year={2017},
    eprint={1703.07737},
    archivePrefix={arXiv},
    primaryClass={cs.CV}
}