Sentence Similarity
sentence-transformers
Safetensors
modernbert
feature-extraction
dense
Generated from Trainer
dataset_size:277492
loss:CachedMultipleNegativesRankingLoss
Eval Results (legacy)
text-embeddings-inference
Instructions to use benjamintli/modernbert-code-v4-hard-negatives with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use benjamintli/modernbert-code-v4-hard-negatives with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("benjamintli/modernbert-code-v4-hard-negatives") sentences = [ "// Uint is a helper routine that allocates a new uint value to store v and\n// returns a pointer to it. This is useful when assigning optional parameters.", "func (c *Animation) GetCurrentTimeWithParams(v *AnimationGetCurrentTimeParams) (float64, error) {\n\tresp, err := gcdmessage.SendCustomReturn(c.target, c.target.GetSendCh(), &gcdmessage.ParamRequest{Id: c.target.GetId(), Method: \"Animation.getCurrentTime\", Params: v})\n\tif err != nil {\n\t\treturn 0, err\n\t}\n\n\tvar chromeData struct {\n\t\tResult struct {\n\t\t\tCurrentTime float64\n\t\t}\n\t}\n\n\tif resp == nil {\n\t\treturn 0, &gcdmessage.ChromeEmptyResponseErr{}\n\t}\n\n\t// test if error first\n\tcerr := &gcdmessage.ChromeErrorResponse{}\n\tjson.Unmarshal(resp.Data, cerr)\n\tif cerr != nil && cerr.Error != nil {\n\t\treturn 0, &gcdmessage.ChromeRequestErr{Resp: cerr}\n\t}\n\n\tif err := json.Unmarshal(resp.Data, &chromeData); err != nil {\n\t\treturn 0, err\n\t}\n\n\treturn chromeData.Result.CurrentTime, nil\n}", "func Uint(v uint) *uint {\n\tp := new(uint)\n\t*p = v\n\treturn p\n}", "def after_init_app(self, app: FlaskUnchained):\n \"\"\"\n Configure the JSON encoder for Flask to be able to serialize Enums,\n LocalProxy objects, and SQLAlchemy models.\n \"\"\"\n self.set_json_encoder(app)\n app.before_first_request(self.register_model_resources)" ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Notebooks
- Google Colab
- Kaggle
| { | |
| "architectures": [ | |
| "ModernBertModel" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 50281, | |
| "classifier_activation": "gelu", | |
| "classifier_bias": false, | |
| "classifier_dropout": 0.0, | |
| "classifier_pooling": "mean", | |
| "cls_token_id": 50281, | |
| "decoder_bias": true, | |
| "deterministic_flash_attn": false, | |
| "dtype": "float32", | |
| "embedding_dropout": 0.0, | |
| "eos_token_id": 50282, | |
| "global_attn_every_n_layers": 3, | |
| "gradient_checkpointing": false, | |
| "hidden_activation": "gelu", | |
| "hidden_size": 768, | |
| "initializer_cutoff_factor": 2.0, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 1152, | |
| "layer_norm_eps": 1e-05, | |
| "layer_types": [ | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention" | |
| ], | |
| "local_attention": 128, | |
| "max_position_embeddings": 8192, | |
| "mlp_bias": false, | |
| "mlp_dropout": 0.0, | |
| "model_type": "modernbert", | |
| "norm_bias": false, | |
| "norm_eps": 1e-05, | |
| "num_attention_heads": 12, | |
| "num_hidden_layers": 22, | |
| "pad_token_id": 50283, | |
| "position_embedding_type": "absolute", | |
| "repad_logits_with_grad": false, | |
| "rope_parameters": { | |
| "full_attention": { | |
| "rope_theta": 160000.0, | |
| "rope_type": "default" | |
| }, | |
| "sliding_attention": { | |
| "rope_theta": 10000.0, | |
| "rope_type": "default" | |
| } | |
| }, | |
| "sep_token_id": 50282, | |
| "sparse_pred_ignore_index": -100, | |
| "sparse_prediction": false, | |
| "tie_word_embeddings": true, | |
| "transformers_version": "5.0.0", | |
| "vocab_size": 50368 | |
| } | |