{ | |
"architectures": [ | |
"Qwen2ForCausalLM" | |
], | |
"attention_dropout": 0.0, | |
"eos_token_id": 151645, | |
"hidden_act": "silu", | |
"hidden_size": 1536, | |
"initializer_range": 0.02, | |
"intermediate_size": 8960, | |
"max_position_embeddings": 131072, | |
"max_window_layers": 28, | |
"model_type": "qwen2", | |
"num_attention_heads": 12, | |
"num_hidden_layers": 28, | |
"num_key_value_heads": 2, | |
"quantization": { | |
"group_size": 64, | |
"bits": "2" | |
}, | |
"rms_norm_eps": 1e-06, | |
"rope_theta": 1000000.0, | |
"sliding_window": 131072, | |
"tie_word_embeddings": true, | |
"torch_dtype": "bfloat16", | |
"transformers_version": "4.41.1", | |
"use_cache": false, | |
"use_sliding_window": false, | |
"vocab_size": 151936 | |
} |