Text Classification
Transformers
Safetensors
modernbert
routing
llm-routing
prompt-classification
multilingual
text-embeddings-inference
Instructions to use scombat/s1d1-router-6src-tiny with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use scombat/s1d1-router-6src-tiny with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="scombat/s1d1-router-6src-tiny")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("scombat/s1d1-router-6src-tiny") model = AutoModelForSequenceClassification.from_pretrained("scombat/s1d1-router-6src-tiny", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download config.json from scombat/s1d1-router-6src-tiny: direct link, hf CLI and curl.
- Browser
- Download file 2.99 kB
-
https://huggingface.co/scombat/s1d1-router-6src-tiny/resolve/main/config.json
- Command line
-
hf download hf://scombat/s1d1-router-6src-tiny/config.json
-
curl -L -o config.json https://huggingface.co/scombat/s1d1-router-6src-tiny/resolve/main/config.json
2.99 kB
| { | |
| "architectures": [ | |
| "ModernBertForSequenceClassification" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "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": "float16", | |
| "embedding_dropout": 0.0, | |
| "eos_token_id": 1, | |
| "global_attn_every_n_layers": 3, | |
| "gradient_checkpointing": false, | |
| "hidden_activation": "gelu", | |
| "hidden_size": 384, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1", | |
| "2": "LABEL_2", | |
| "3": "LABEL_3", | |
| "4": "LABEL_4", | |
| "5": "LABEL_5", | |
| "6": "LABEL_6", | |
| "7": "LABEL_7", | |
| "8": "LABEL_8", | |
| "9": "LABEL_9", | |
| "10": "LABEL_10", | |
| "11": "LABEL_11", | |
| "12": "LABEL_12", | |
| "13": "LABEL_13", | |
| "14": "LABEL_14", | |
| "15": "LABEL_15", | |
| "16": "LABEL_16", | |
| "17": "LABEL_17", | |
| "18": "LABEL_18", | |
| "19": "LABEL_19", | |
| "20": "LABEL_20" | |
| }, | |
| "initializer_cutoff_factor": 2.0, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 1152, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1, | |
| "LABEL_10": 10, | |
| "LABEL_11": 11, | |
| "LABEL_12": 12, | |
| "LABEL_13": 13, | |
| "LABEL_14": 14, | |
| "LABEL_15": 15, | |
| "LABEL_16": 16, | |
| "LABEL_17": 17, | |
| "LABEL_18": 18, | |
| "LABEL_19": 19, | |
| "LABEL_2": 2, | |
| "LABEL_20": 20, | |
| "LABEL_3": 3, | |
| "LABEL_4": 4, | |
| "LABEL_5": 5, | |
| "LABEL_6": 6, | |
| "LABEL_7": 7, | |
| "LABEL_8": 8, | |
| "LABEL_9": 9 | |
| }, | |
| "layer_norm_eps": 1e-05, | |
| "layer_types": [ | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention" | |
| ], | |
| "local_attention": 128, | |
| "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": 6, | |
| "num_hidden_layers": 6, | |
| "pad_token_id": 0, | |
| "position_embedding_type": "sans_pos", | |
| "rope_parameters": { | |
| "full_attention": { | |
| "rope_theta": 160000, | |
| "rope_type": "default" | |
| }, | |
| "sliding_attention": { | |
| "rope_theta": 160000, | |
| "rope_type": "default" | |
| } | |
| }, | |
| "sep_token_id": 1, | |
| "sparse_pred_ignore_index": -100, | |
| "sparse_prediction": false, | |
| "tie_word_embeddings": true, | |
| "transformers_version": "5.19.0", | |
| "vocab_size": 32253, | |
| "problem_type": "regression", | |
| "task_names": [ | |
| "information_seeking", | |
| "reasoning", | |
| "planning", | |
| "editing", | |
| "summarization", | |
| "extraction", | |
| "classification", | |
| "translation", | |
| "coding_debugging", | |
| "math", | |
| "data_analysis", | |
| "writing", | |
| "role_playing", | |
| "advice_seeking", | |
| "brainstorming", | |
| "completion", | |
| "action_execution", | |
| "chat", | |
| "other" | |
| ], | |
| "output_layout": "0: complexity in tier units (score = 0.5 + 0.25 * logit, clipped to 0.01..1.00); 1-19: task logits in task_names order; 20: needs_tools logit" | |
| } | |