| { | |
| "architectures": [ | |
| "AndesVLForConditionalGeneration" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "configuration_andesvl.AndesVLConfig", | |
| "AutoModel": "modeling_andesvl.AndesVLForConditionalGeneration", | |
| "AutoModelForCausalLM": "modeling_andesvl.AndesVLForConditionalGeneration" | |
| }, | |
| "model_type": "andesvl-aimv2-qwen3", | |
| "text_config": { | |
| "vocab_size": 151936, | |
| "max_position_embeddings": 262144, | |
| "hidden_size": 2560, | |
| "intermediate_size": 9728, | |
| "num_hidden_layers": 36, | |
| "num_attention_heads": 32, | |
| "use_sliding_window": false, | |
| "sliding_window": null, | |
| "max_window_layers": 36, | |
| "num_key_value_heads": 8, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "initializer_range": 0.02, | |
| "rms_norm_eps": 1e-06, | |
| "use_cache": true, | |
| "rope_theta": 5000000, | |
| "rope_scaling": null, | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "tie_word_embeddings": true, | |
| "architectures": [ | |
| "Qwen3ForCausalLM" | |
| ], | |
| "bos_token_id": 151643, | |
| "eos_token_id": 151645, | |
| "model_type": "qwen3" | |
| }, | |
| "vision_config": { | |
| "attention_dropout": 0.0, | |
| "disable_rope": false, | |
| "fullatt_block_indexes": null, | |
| "hidden_size": 1024, | |
| "hidden_stride": 2, | |
| "image_size": 448, | |
| "intermediate_size": 2816, | |
| "interpolate_pe_method": "two_dim", | |
| "model_type": "aimv2", | |
| "num_attention_heads": 8, | |
| "num_channels": 3, | |
| "num_hidden_layers": 24, | |
| "patch_size": 14, | |
| "preserve_original_pe": true, | |
| "projection_dropout": 0.0, | |
| "qkv_bias": false, | |
| "rms_norm_eps": 1e-05, | |
| "temporal_patch_size": 1, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.52.4", | |
| "use_bias": false, | |
| "window_size": 112 | |
| }, | |
| "tie_word_embeddings": true, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.51.0" | |
| } |