|
{ |
|
"_name_or_path": "Qwen/Qwen2.5-1.5B", |
|
"architectures": [ |
|
"BertForSequenceClassification" |
|
], |
|
"attention_dropout": 0.0, |
|
"bos_token_id": 151643, |
|
"eos_token_id": 151643, |
|
"hidden_act": "silu", |
|
"hidden_size": 1536, |
|
"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" |
|
}, |
|
"initializer_range": 0.02, |
|
"intermediate_size": 8960, |
|
"label2id": { |
|
"LABEL_0": 0, |
|
"LABEL_1": 1, |
|
"LABEL_10": 10, |
|
"LABEL_11": 11, |
|
"LABEL_2": 2, |
|
"LABEL_3": 3, |
|
"LABEL_4": 4, |
|
"LABEL_5": 5, |
|
"LABEL_6": 6, |
|
"LABEL_7": 7, |
|
"LABEL_8": 8, |
|
"LABEL_9": 9 |
|
}, |
|
"max_position_embeddings": 131072, |
|
"max_window_layers": 28, |
|
"model_type": "qwen2", |
|
"num_attention_heads": 12, |
|
"num_hidden_layers": 28, |
|
"num_key_value_heads": 2, |
|
"pad_token_id": 151643, |
|
"rms_norm_eps": 1e-06, |
|
"rope_scaling": null, |
|
"rope_theta": 1000000.0, |
|
"sliding_window": null, |
|
"tie_word_embeddings": true, |
|
"torch_dtype": "bfloat16", |
|
"transformers_version": "4.45.2", |
|
"use_cache": true, |
|
"use_mrope": false, |
|
"use_sliding_window": false, |
|
"vocab_size": 151936 |
|
} |
|
|