Text Classification
Laya
Safetensors
English
decision-model
system-one
calibrated-decisions
rlcd
ettin
classification
routing
spoken-language-understanding
speech
on-device
Eval Results (legacy)
Instructions to use igorktech/femto-jev with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Laya
How to use igorktech/femto-jev with Laya:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
File size: 1,824 Bytes
aaed4a7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 | {
"transformers_version": "5.22.2",
"architectures": [
"ModernBertForMaskedLM"
],
"output_hidden_states": false,
"return_dict": true,
"dtype": "float32",
"chunk_size_feed_forward": 0,
"is_encoder_decoder": false,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1
},
"problem_type": null,
"vocab_size": 50368,
"hidden_size": 256,
"intermediate_size": 384,
"num_hidden_layers": 7,
"num_attention_heads": 4,
"hidden_activation": "gelu",
"max_position_embeddings": 7999,
"initializer_range": 0.02,
"initializer_cutoff_factor": 2.0,
"norm_eps": 1e-05,
"norm_bias": false,
"pad_token_id": 50283,
"eos_token_id": 50282,
"bos_token_id": 50281,
"cls_token_id": 50281,
"sep_token_id": 50282,
"attention_bias": false,
"attention_dropout": 0.0,
"layer_types": [
"full_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"full_attention"
],
"rope_parameters": {
"sliding_attention": {
"rope_type": "default",
"rope_theta": 160000.0
},
"full_attention": {
"rope_type": "default",
"rope_theta": 160000.0
}
},
"local_attention": 128,
"embedding_dropout": 0.0,
"mlp_bias": false,
"mlp_dropout": 0.0,
"decoder_bias": true,
"classifier_pooling": "mean",
"classifier_dropout": 0.0,
"classifier_bias": false,
"classifier_activation": "gelu",
"deterministic_flash_attn": false,
"sparse_prediction": false,
"sparse_pred_ignore_index": -100,
"tie_word_embeddings": true,
"_name_or_path": "jhu-clsp/ettin-encoder-17m",
"global_attn_every_n_layers": 3,
"gradient_checkpointing": false,
"layer_norm_eps": 1e-05,
"model_type": "modernbert",
"position_embedding_type": "sans_pos",
"is_causal": false,
"causal_mask": false,
"output_attentions": false
} |