Shuu12121/CodeSearch-ModernBERT-Crow-v3-large-len1024-Plus

SentenceTransformer based on Shuu12121/CodeModernBERT-Crow-v3-large-len1024

This is a sentence-transformers model finetuned from Shuu12121/CodeModernBERT-Crow-v3-large-len1024. It maps sentences & paragraphs to a 1024-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: Shuu12121/CodeModernBERT-Crow-v3-large-len1024
• Maximum Sequence Length: 1024 tokens
• Output Dimensionality: 1024 dimensions
• 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': 1024, 'do_lower_case': False, 'architecture': 'ModernBertModel'})
  (1): Pooling({'word_embedding_dimension': 1024, '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})
)

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 = [
    'OnEachBatchTx registers a handler for a specific event type that is contingent on a transaction.',
    'func OnEachBatchTx[T, TTx comparable](b *Bus, fn func(ctx context.Context, tx TTx, data []T) error) {\n\tsub := findBus[T, TTx](b)\n\tsub.onBatchTx = append(sub.onBatchTx, fn)\n}',
    'func (s *GetDomainDetailOutput) SetAbuseContactEmail(v string) *GetDomainDetailOutput {\n\ts.AbuseContactEmail = &v\n\treturn s\n}',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 1024]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[1.0000, 0.7953, 0.0445],
#         [0.7953, 1.0000, 0.0267],
#         [0.0445, 0.0267, 1.0000]])

Training Details

Training Dataset

Unnamed Dataset

• Size: 8,003,584 training samples
• Columns: sentence_0, sentence_1, and label
• Approximate statistics based on the first 1000 samples:

  	sentence_0	sentence_1	label
  type	string	string	float
  details	min: 8 tokens mean: 36.78 tokens max: 1024 tokens	min: 15 tokens mean: 165.61 tokens max: 1024 tokens	min: 1.0 mean: 1.0 max: 1.0

• Samples:

  sentence_0	sentence_1	label
  Generated from example definition: https://github.com/Azure/azure-rest-api-specs/blob/ee1eec42dcc710ff88db2d1bf574b2f9afe3d654/specification/eventgrid/resource-manager/Microsoft.EventGrid/stable/2025-02-15/examples/DomainTopicEventSubscriptions_Delete.json	func ExampleDomainTopicEventSubscriptionsClient_BeginDelete() { cred, err := azidentity.NewDefaultAzureCredential(nil) if err != nil { log.Fatalf("failed to obtain a credential: %v", err) } ctx := context.Background() clientFactory, err := armeventgrid.NewClientFactory("", cred, nil) if err != nil { log.Fatalf("failed to create client: %v", err) } poller, err := clientFactory.NewDomainTopicEventSubscriptionsClient().BeginDelete(ctx, "examplerg", "exampleDomain1", "exampleDomainTopic1", "examplesubscription1", nil) if err != nil { log.Fatalf("failed to finish the request: %v", err) } _, err = poller.PollUntilDone(ctx, nil) if err != nil { log.Fatalf("failed to pull the result: %v", err) } }	1.0
  newUpgradeContext creates a Context, avoid nil Context member. only used for testing now.	func newUpgradeContext() Context { return Context{ Context: context.Background(), SubTaskConfigs: make(map[string]map[string]config.SubTaskConfig), } }	1.0
  ToPostRequestInformation create new navigation property to rules for policies	func (m *RoleManagementPoliciesItemRulesRequestBuilder) ToPostRequestInformation(ctx context.Context, body iadcd81124412c61e647227ecfc4449d8bba17de0380ddda76f641a29edf2b242.UnifiedRoleManagementPolicyRuleable, requestConfiguration *RoleManagementPoliciesItemRulesRequestBuilderPostRequestConfiguration)(*i2ae4187f7daee263371cb1c977df639813ab50ffa529013b7437480d1ec0158f.RequestInformation, error) { requestInfo := i2ae4187f7daee263371cb1c977df639813ab50ffa529013b7437480d1ec0158f.NewRequestInformation() requestInfo.UrlTemplate = m.urlTemplate requestInfo.PathParameters = m.pathParameters requestInfo.Method = i2ae4187f7daee263371cb1c977df639813ab50ffa529013b7437480d1ec0158f.POST requestInfo.Headers.Add("Accept", "application/json") err := requestInfo.SetContentFromParsable(ctx, m.requestAdapter, "application/json", body) if err != nil { return nil, err } if requestConfiguration != nil { requestInfo.Headers.AddAll(requestConfiguration.Header...	1.0

• Loss: CachedMultipleNegativesRankingLoss with these parameters:

  {
      "scale": 20.0,
      "similarity_fct": "cos_sim",
      "mini_batch_size": 32,
      "gather_across_devices": false
  }
  

Training Hyperparameters

Non-Default Hyperparameters

• per_device_train_batch_size: 1024
• per_device_eval_batch_size: 1024
• num_train_epochs: 1
• fp16: True
• multi_dataset_batch_sampler: round_robin

All Hyperparameters

Click to expand

• overwrite_output_dir: False
• do_predict: False
• eval_strategy: no
• prediction_loss_only: True
• per_device_train_batch_size: 1024
• per_device_eval_batch_size: 1024
• 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: 1
• 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_fused
• 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: {}

Training Logs

Epoch	Step	Training Loss
0.0640	500	0.6221
0.1279	1000	0.1793
0.1919	1500	0.1571
0.2559	2000	0.1442
0.3199	2500	0.1323
0.3838	3000	0.124
0.4478	3500	0.1165
0.5118	4000	0.1105
0.5757	4500	0.1042
0.6397	5000	0.099
0.7037	5500	0.0966
0.7677	6000	0.0914
0.8316	6500	0.0893
0.8956	7000	0.0876
0.9596	7500	0.086

Framework Versions

• Python: 3.10.12
• Sentence Transformers: 5.2.0
• Transformers: 4.57.3
• PyTorch: 2.8.0+cu128
• Accelerate: 1.12.0
• Datasets: 3.6.0
• 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",
}

CachedMultipleNegativesRankingLoss

@misc{gao2021scaling,
    title={Scaling Deep Contrastive Learning Batch Size under Memory Limited Setup},
    author={Luyu Gao and Yunyi Zhang and Jiawei Han and Jamie Callan},
    year={2021},
    eprint={2101.06983},
    archivePrefix={arXiv},
    primaryClass={cs.LG}
}