| { | |
| "architectures": [ | |
| "Qwen2_5OmniThinkerForCausalLM" | |
| ], | |
| "attention_dropout": 0.0, | |
| "auto_map": { | |
| "AutoConfig": "AlexHung29629/Qwen-2.5-Omni-ThinkerTextModel2--modeling_qwen_thinker.Qwen2_5OmniTextConfig", | |
| "AutoModelForCausalLM": "AlexHung29629/Qwen-2.5-Omni-ThinkerTextModel2--modeling_qwen_thinker.Qwen2_5OmniThinkerForCausalLM" | |
| }, | |
| "hidden_act": "silu", | |
| "hidden_size": 3584, | |
| "init_std": 0.02, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 18944, | |
| "max_position_embeddings": 32768, | |
| "max_window_layers": 28, | |
| "model_type": "qwen2_5_omni_text", | |
| "num_attention_heads": 28, | |
| "num_hidden_layers": 28, | |
| "num_key_value_heads": 4, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": { | |
| "mrope_section": [ | |
| 16, | |
| 24, | |
| 24 | |
| ], | |
| "rope_type": "default", | |
| "type": "default" | |
| }, | |
| "rope_theta": 1000000.0, | |
| "sliding_window": 32768, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.52.0.dev0", | |
| "use_cache": false, | |
| "use_sliding_window": false, | |
| "vocab_size": 152064 | |
| } | |