Sentence Similarity
sentence-transformers
Safetensors
modernbert
feature-extraction
dense
Generated from Trainer
dataset_size:58800
loss:MultipleNegativesRankingLoss
text-embeddings-inference
Instructions to use Shuu12121/CodeSearch-ModernBERT-Finch-SmallBatch with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use Shuu12121/CodeSearch-ModernBERT-Finch-SmallBatch with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("Shuu12121/CodeSearch-ModernBERT-Finch-SmallBatch") sentences = [ "Returns boolean indicating whether the requestUrl matches against the paths configured.\n\n@param requestedUrl - url requested by user\n@param opts - unless configuration\n@returns {boolean}", "def xmoe2_v1_l4k_global_only():\n \"\"\"\"\"\"\n hparams = xmoe2_v1_l4k()\n hparams.decoder_layers = [\n \"att\" if l == \"local_att\" else l for l in hparams.decoder_layers]\n return hparams", "function matchesPath(requestedUrl, opts) {\n var paths = !opts.path || Array.isArray(opts.path) ?\n opts.path : [opts.path];\n\n if (paths) {\n return paths.some(function(p) {\n return (typeof p === 'string' && p === requestedUrl.pathname) ||\n (p instanceof RegExp && !! p.exec(requestedUrl.pathname));\n });\n }\n\n return false;\n}", "public static function factory($accessToken, $currentTeam)\n {\n $client = Client::factory($accessToken);\n\n return new self($client, $currentTeam);\n }" ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Notebooks
- Google Colab
- Kaggle
| { | |
| "model_type": "SentenceTransformer", | |
| "__version__": { | |
| "sentence_transformers": "5.0.0", | |
| "transformers": "4.53.1", | |
| "pytorch": "2.7.0+cu128" | |
| }, | |
| "prompts": { | |
| "query": "", | |
| "document": "" | |
| }, | |
| "default_prompt_name": null, | |
| "similarity_fn_name": "cosine" | |
| } |