| { | |
| "architectures": [ | |
| "Qwen3ForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 151643, | |
| "eos_token_id": 151643, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 2560, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 9728, | |
| "max_position_embeddings": 131072, | |
| "max_window_layers": 36, | |
| "mix_coeff": 0, | |
| "model_type": "qwen3", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 36, | |
| "num_key_value_heads": 8, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": null, | |
| "rope_theta": 1000000, | |
| "sliding_window": null, | |
| "tie_word_embeddings": true, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.51.0", | |
| "use_cache": true, | |
| "use_sliding_window": false, | |
| "vocab_size": 151937, | |
| "summary_token_begin": 151936, | |
| "summary_chunk_size": 8, | |
| "summary_token_num": 1, | |
| "use_summary_attention": true, | |
| "summary_sliding_chunk_num": "([128]*3+[16768]*1)*9", | |
| "summary_layer_freq": "([1])*36", | |
| "summary_chunk_position_ids_type": "origin", | |
| "summary_token_position_ids_type": "last_chunk_slice_right", | |
| "summary_independent_parameters": true, | |
| "summary_independent_attention_layernorm": false, | |
| "auto_map": { | |
| "AutoModel": "modeling_qwen3.Qwen3Model", | |
| "AutoModelForCausalLM": "modeling_qwen3.Qwen3ForCausalLM" | |
| } | |
| } | |