|
{ |
|
"_name_or_path": "hugosousa/smol-135-c-3ed00d05", |
|
"architectures": [ |
|
"ContextClassifier" |
|
], |
|
"attention_bias": false, |
|
"attention_dropout": 0.0, |
|
"bos_token_id": 0, |
|
"eos_token_id": 0, |
|
"finetuning_task": "text-classification", |
|
"head_dim": 64, |
|
"hidden_act": "silu", |
|
"hidden_size": 576, |
|
"id2label": { |
|
"0": ">", |
|
"1": "<", |
|
"2": "=" |
|
}, |
|
"initializer_range": 0.041666666666666664, |
|
"intermediate_size": 1536, |
|
"is_llama_config": true, |
|
"label2id": { |
|
"<": 1, |
|
"=": 2, |
|
">": 0 |
|
}, |
|
"max_position_embeddings": 8192, |
|
"mlp_bias": false, |
|
"model_type": "llama", |
|
"n_score_hidden_layers": 2, |
|
"num_attention_heads": 9, |
|
"num_hidden_layers": 30, |
|
"num_key_value_heads": 3, |
|
"pad_token_id": 0, |
|
"pretraining_tp": 1, |
|
"rms_norm_eps": 1e-05, |
|
"rope_interleaved": false, |
|
"rope_scaling": null, |
|
"rope_theta": 100000, |
|
"tie_word_embeddings": true, |
|
"tokens_to_encode_ids": [ |
|
49152, |
|
49153, |
|
49154, |
|
49155, |
|
49156, |
|
49157, |
|
49158, |
|
49159 |
|
], |
|
"torch_dtype": "bfloat16", |
|
"transformers_version": "4.47.1", |
|
"use_cache": true, |
|
"vocab_size": 49160 |
|
} |
|
|