Text Classification
Transformers
Safetensors
modernbert
code
language-identification
multi-label
llm-guard
encoder
text-embeddings-inference
Instructions to use Accuknoxtechnologies/CodeLanguage-Encoder-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Accuknoxtechnologies/CodeLanguage-Encoder-v1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="Accuknoxtechnologies/CodeLanguage-Encoder-v1")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("Accuknoxtechnologies/CodeLanguage-Encoder-v1") model = AutoModelForSequenceClassification.from_pretrained("Accuknoxtechnologies/CodeLanguage-Encoder-v1") - Notebooks
- Google Colab
- Kaggle
| { | |
| "architectures": [ | |
| "ModernBertForSequenceClassification" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "base_model": "jhu-clsp/mmBERT-base", | |
| "bos_token_id": 2, | |
| "classifier_activation": "gelu", | |
| "classifier_bias": false, | |
| "classifier_dropout": 0.0, | |
| "classifier_pooling": "mean", | |
| "cls_token_id": 1, | |
| "decoder_bias": true, | |
| "deterministic_flash_attn": false, | |
| "dtype": "float32", | |
| "embedding_dropout": 0.0, | |
| "eos_token_id": 1, | |
| "global_attn_every_n_layers": 3, | |
| "global_rope_theta": 160000, | |
| "gradient_checkpointing": false, | |
| "hidden_activation": "gelu", | |
| "hidden_size": 768, | |
| "id2label": { | |
| "0": "Python", | |
| "1": "JavaScript", | |
| "2": "Java", | |
| "3": "C", | |
| "4": "C++", | |
| "5": "C#", | |
| "6": "Go", | |
| "7": "Rust", | |
| "8": "Kotlin", | |
| "9": "Swift", | |
| "10": "Ruby", | |
| "11": "R", | |
| "12": "Scala", | |
| "13": "Perl", | |
| "14": "Lua", | |
| "15": "Bash", | |
| "16": "PowerShell", | |
| "17": "Batch", | |
| "18": "SQL", | |
| "19": "Dockerfile", | |
| "20": "YAML", | |
| "21": "Makefile", | |
| "22": "Terraform", | |
| "23": "AWK", | |
| "24": "jq" | |
| }, | |
| "initializer_cutoff_factor": 2.0, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 1152, | |
| "label2id": { | |
| "AWK": 23, | |
| "Bash": 15, | |
| "Batch": 17, | |
| "C": 3, | |
| "C#": 5, | |
| "C++": 4, | |
| "Dockerfile": 19, | |
| "Go": 6, | |
| "Java": 2, | |
| "JavaScript": 1, | |
| "Kotlin": 8, | |
| "Lua": 14, | |
| "Makefile": 21, | |
| "Perl": 13, | |
| "PowerShell": 16, | |
| "Python": 0, | |
| "R": 11, | |
| "Ruby": 10, | |
| "Rust": 7, | |
| "SQL": 18, | |
| "Scala": 12, | |
| "Swift": 9, | |
| "Terraform": 22, | |
| "YAML": 20, | |
| "jq": 24 | |
| }, | |
| "layer_norm_eps": 1e-05, | |
| "local_attention": 128, | |
| "local_rope_theta": 160000, | |
| "mask_token_id": 4, | |
| "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": 0, | |
| "position_embedding_type": "sans_pos", | |
| "problem_type": "multi_label_classification", | |
| "repad_logits_with_grad": false, | |
| "sep_token_id": 1, | |
| "sparse_pred_ignore_index": -100, | |
| "sparse_prediction": false, | |
| "training_provenance": { | |
| "base_model": "jhu-clsp/mmBERT-base", | |
| "epochs": 2, | |
| "labels": [ | |
| "Python", | |
| "JavaScript", | |
| "Java", | |
| "C", | |
| "C++", | |
| "C#", | |
| "Go", | |
| "Rust", | |
| "Kotlin", | |
| "Swift", | |
| "Ruby", | |
| "R", | |
| "Scala", | |
| "Perl", | |
| "Lua", | |
| "Bash", | |
| "PowerShell", | |
| "Batch", | |
| "SQL", | |
| "Dockerfile", | |
| "YAML", | |
| "Makefile", | |
| "Terraform", | |
| "AWK", | |
| "jq" | |
| ], | |
| "learning_rate": 2e-05, | |
| "max_seq_length": 3072, | |
| "problem_type": "multi_label_classification", | |
| "task": "code-language-identification", | |
| "threshold": 0.5, | |
| "trained_at": "2026-06-02T09:22:34+00:00" | |
| }, | |
| "transformers_version": "4.57.6", | |
| "vocab_size": 256000 | |
| } | |