| { | |
| "_name_or_path": "small", | |
| "architectures": [ | |
| "MistralForSequenceClassification" | |
| ], | |
| "attention_dropout": 0.0, | |
| "auto_map": { | |
| "AutoModel": "mesolitica/malaysian-mistral-191M-MLM-512--bidirectional_mistral.MistralBiForMNTP" | |
| }, | |
| "bos_token_id": 1, | |
| "eos_token_id": 2, | |
| "hidden_act": "silu", | |
| "hidden_size": 768, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1", | |
| "2": "LABEL_2" | |
| }, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3072, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1, | |
| "LABEL_2": 2 | |
| }, | |
| "max_position_embeddings": 4096, | |
| "model_type": "mistral", | |
| "num_attention_heads": 16, | |
| "num_hidden_layers": 16, | |
| "num_key_value_heads": 8, | |
| "pad_token_id": 0, | |
| "problem_type": "single_label_classification", | |
| "rms_norm_eps": 1e-05, | |
| "rope_theta": 10000.0, | |
| "sliding_window": 4096, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.40.1", | |
| "use_cache": true, | |
| "vocab": [ | |
| "negative", | |
| "neutral", | |
| "positive" | |
| ], | |
| "vocab_size": 32000 | |
| } | |