bge-base-en-v1.5-ds-rag-s

SentenceTransformer

This is a sentence-transformers model trained. It maps sentences & paragraphs to a 768-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:** [Unknown](https://huggingface.co/unknown) -->

• Maximum Sequence Length: 512 tokens
• Output Dimensionality: 768 dimensions
• Similarity Function: Cosine Similarity

<!-- - **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({'max_seq_length': 512, 'do_lower_case': True, 'architecture': 'BertModel'})
  (1): Pooling({'word_embedding_dimension': 768, '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("sentence_transformers_model_id")
# Run inference
sentences = [
    'The more recent works of Sutton et al. [SMS99], Baxter and Bartlett  [BaB01] , Konda and Tsitsiklis  [KoT99] ,  [KoT03] , Marbach and Tsitsiklis  [MaT01] ,  [MaT03] , Peters and Schaal  [PeS08] , and Bhatnagar et al. [BSG09]  have been influential; see also the survey by Grondman et al. Actor-critic algorithms that are suitable for POMDP and involve gradient estimation have been given by H. Yu [Yu05], and Estanjini, Li, and Paschalidis  [ELP12] .',
    'Random search methods: The cross-entropy method was initially developed in the context of rare event simulation and was later adapted for use in optimization. For textbook accounts, see Rubinstein and Kroese  [RuK04] ,  [RuK13] ,  [RuK16] , and Busoniu et al.',
    '3.8 Using the Gram-Schmidt method, turn the basis B = (b 1 , b 2 ) of a twodimensional subspace U ⊆ R 3 into an ONB C = (c 1 , c 2 ) of U , where\n\n3.9 Let n ∈ N and let x 1 , . , xn > 0 be n positive real numbers so that x 1 + .',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[1.0000, 0.5664, 0.2820],
#         [0.5664, 1.0000, 0.2084],
#         [0.2820, 0.2084, 1.0000]])

<!-- ### 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

Semantic Similarity

• Dataset: val
• Evaluated with <code>EmbeddingSimilarityEvaluator</code>

<!-- ## 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: 40,806 training samples
• Columns: <code>sentence_0</code> and <code>sentence_1</code>
• Approximate statistics based on the first 1000 samples:

  	sentence_0	sentence_1
  type	string	string
  details	<ul><li>min: 7 tokens</li><li>mean: 128.61 tokens</li><li>max: 512 tokens</li></ul>	<ul><li>min: 8 tokens</li><li>mean: 125.05 tokens</li><li>max: 512 tokens</li></ul>

• Samples:

  sentence_0	sentence_1
  <code>When both node and edge embeddings are present, we can translate back and forth between the two graphs. Now there are four possible updates (nodes update nodes, nodes update edges, edges update nodes, and edges update edges), and these can be alternated as desired, or with Problem 13.14 minor modifications, nodes can be updated simultaneously from both nodes and edges. Graphs consist of a set of nodes, where pairs of these nodes are connected by edges. Both nodes and edges can have data attached, and these are referred to as node embeddings and edge embeddings, respectively. Many real-world problems can be framed in terms of graphs, where the goal is to establish a property of the entire graph, properties of each node or edge, or the presence of additional edges in the graph. Graph neural networks are deep learning models that are applied to graphs. Since the node order in graphs is arbitrary, the layers of graph neural networks must be equivariant to permutations of the node indices. ...</code>	<code>One challenge of processing graphs is that they often occur in the transductive setting, where there is only one partially labeled graph rather than sets of training and test graphs. This graph can be extremely large, which adds further challenges in terms of training and has led to sampling and partitioning algorithms. The edge graph has a node for every edge in the original graph. By converting to this representation, graph neural networks can be used to update the edge embeddings. This has disadvantages: the filters are not localized, and the decomposition is prohibitively expensive for large graphs. (2015) tackled the first problem by forcing the Fourier representation to be smooth (and hence the spatial domain to be localized). (2016) introduced ChebNet, which approximates the filters efficiently by using the recursive properties of Chebyshev polynomials.</code>
  <code>possible without sacrificing too much of the understanding. You can almost imagine this as a secret shortcut that only you and your family understand but that has been optimized for the topics you frequently discussed. 1 For simplicity and to focus on compression, we chose to ignore the fact that words are an explicit model, although most words also have tremendous context-dependent complexity behind them.</code>	<code>Rather than expressing words or images (for example, machine learning engineer in our example, or JPEG codec for images) in their uncompressed versions, an autoencoder compresses and clusters them based on its understanding of the data. One of the key distinctions with autoencoders is that we end-to-end train the whole network with one loss function, whereas GANs have distinct loss functions for the Generator and the Discriminator. Let's now look at the context in which autoencoders sit compared to GANs. As you can see in figure 2 .1, both are generative models that are subsets of artificial intelligence (AI) and machine learning (ML). In the case<br><br>Generative models of autoencoders (or their variational alternative, VAEs), we have an explicitly written function that we are trying to optimize (a cost function); but in the case of GANs (as you will learn), we do not have an explicit metric as simple as mean squared error, accuracy, or area under the ROC curve to optimize. 2 GANs instea...</code>
  <code>They are generally more complicated than discounted problems, but the preceding results hold under the assumption that there is a bound on the number of stages needed to reach the termination state, regardless of the choices of the minimizer and the maximizer. This condition is fulfilled, for example, in many computer games, like chess, which will be discussed later in this section. The approximation ideas for stochastic optimal control that we have discussed in this chapter are also relevant within the minimax context.</code>	<code>, w N →1 playing the role of "optimization variables/controls." For finite state, control, and disturbance spaces, this is a longest path problem defined on an acyclic graph, since the control variables u k+1 , . , u N →1 are determined by the base policy.</code>

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

  {
      "scale": 20.0,
      "similarity_fct": "cos_sim",
      "gather_across_devices": false
  }
  

Training Hyperparameters

Non-Default Hyperparameters

• per_device_train_batch_size: 16
• per_device_eval_batch_size: 16
• num_train_epochs: 6
• fp16: True
• multi_dataset_batch_sampler: round_robin

All Hyperparameters

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

• 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
• torch_empty_cache_steps: None
• learning_rate: 5e-05
• weight_decay: 0.0
• adam_beta1: 0.9
• adam_beta2: 0.999
• adam_epsilon: 1e-08
• max_grad_norm: 1
• num_train_epochs: 6
• max_steps: -1
• lr_scheduler_type: linear
• lr_scheduler_kwargs: {}
• warmup_ratio: 0.0
• 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
• bf16: False
• fp16: True
• 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
• optim_args: None
• adafactor: False
• group_by_length: False
• length_column_name: length
• project: huggingface
• trackio_space_id: trackio
• 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: no
• 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: True
• prompts: None
• batch_sampler: batch_sampler
• multi_dataset_batch_sampler: round_robin
• router_mapping: {}
• learning_rate_mapping: {}

</details>

Training Logs

Framework Versions

• Python: 3.11.7
• Sentence Transformers: 5.1.1
• Transformers: 4.57.3
• PyTorch: 2.5.1+cu121
• Accelerate: 1.12.0
• Datasets: 4.4.1
• Tokenizers: 0.22.1

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",
}

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}
}

If you use this model, please cite:

@misc{aghakhani2025synergsticrag,
  author       = {Danial Aghakhani Zadeh},
  title        = {Fine-tuned bge-base-en-v1.5 for Data Science RAG},
  year         = {2025},
  publisher    = {Hugging Face},
  howpublished = {\url{https://huggingface.co/DigitalAsocial/bge-base-en-v1.5-ds-rag-s}}
}

<!-- ## 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.* -->