{ | |
"_name_or_path": "Qwen/Qwen1.5-1.8B", | |
"architectures": [ | |
"Qwen2ForSequenceClassification" | |
], | |
"attention_dropout": 0.0, | |
"bos_token_id": 151643, | |
"eos_token_id": 151643, | |
"finetuning_task": "text-classification", | |
"hidden_act": "silu", | |
"hidden_size": 2048, | |
"id2label": { | |
"0": "0", | |
"1": "1", | |
"2": "10", | |
"3": "11", | |
"4": "12", | |
"5": "13", | |
"6": "14", | |
"7": "15", | |
"8": "16", | |
"9": "17", | |
"10": "18", | |
"11": "19", | |
"12": "2", | |
"13": "20", | |
"14": "21", | |
"15": "22", | |
"16": "3", | |
"17": "4", | |
"18": "5", | |
"19": "6", | |
"20": "7", | |
"21": "8", | |
"22": "9" | |
}, | |
"initializer_range": 0.02, | |
"intermediate_size": 5504, | |
"label2id": { | |
"0": 0, | |
"1": 1, | |
"10": 2, | |
"11": 3, | |
"12": 4, | |
"13": 5, | |
"14": 6, | |
"15": 7, | |
"16": 8, | |
"17": 9, | |
"18": 10, | |
"19": 11, | |
"2": 12, | |
"20": 13, | |
"21": 14, | |
"22": 15, | |
"3": 16, | |
"4": 17, | |
"5": 18, | |
"6": 19, | |
"7": 20, | |
"8": 21, | |
"9": 22 | |
}, | |
"max_position_embeddings": 32768, | |
"max_window_layers": 21, | |
"model_type": "qwen2", | |
"num_attention_heads": 16, | |
"num_hidden_layers": 24, | |
"num_key_value_heads": 16, | |
"pad_token_id": 151643, | |
"problem_type": "single_label_classification", | |
"rms_norm_eps": 1e-06, | |
"rope_theta": 1000000.0, | |
"sliding_window": 32768, | |
"tie_word_embeddings": false, | |
"torch_dtype": "bfloat16", | |
"transformers_version": "4.39.0.dev0", | |
"use_cache": true, | |
"use_sliding_window": false, | |
"vocab_size": 151646 | |
} | |