{ | |
"_model_name_or_path": "080d25a068c29293eff9f3b84eafdb53e489d138", | |
"architectures": [ | |
"Qwen3ForCausalLM" | |
], | |
"attention_bias": false, | |
"attention_dropout": 0.0, | |
"bos_token_id": 151643, | |
"eos_token_id": 151645, | |
"head_dim": 128, | |
"hidden_act": "silu", | |
"hidden_size": 5120, | |
"initializer_range": 0.02, | |
"intermediate_size": 25600, | |
"max_position_embeddings": 40960, | |
"max_window_layers": 28, | |
"model_type": "qwen3", | |
"num_attention_heads": 64, | |
"num_hidden_layers": 64, | |
"num_key_value_heads": 8, | |
"rms_norm_eps": 9.999999974752427e-07, | |
"rope_scaling": null, | |
"rope_theta": 1000000.0, | |
"sliding_window": 4096, | |
"tie_word_embeddings": false, | |
"torch_dtype": "float16", | |
"transformers_version": "4.51.3", | |
"use_cache": true, | |
"use_sliding_window": false, | |
"vocab_size": 151936 | |
} | |