| { | |
| "aligner_config": { | |
| "cls": "MlpProjector", | |
| "model_type": "aligner", | |
| "params": { | |
| "depth": 2, | |
| "input_dim": 1024, | |
| "n_embed": 4096, | |
| "projector_type": "mlp_gelu" | |
| } | |
| }, | |
| "architectures": [ | |
| "MultiModalityCausalLM" | |
| ], | |
| "bos_token_id": 100000, | |
| "eos_token_id": 100001, | |
| "gen_aligner_config": { | |
| "cls": "MlpProjector", | |
| "model_type": "gen_aligner", | |
| "params": { | |
| "depth": 2, | |
| "input_dim": 8, | |
| "n_embed": 4096, | |
| "projector_type": "mlp_gelu" | |
| } | |
| }, | |
| "gen_head_config": { | |
| "cls": "vision_head", | |
| "model_type": "gen_head", | |
| "params": { | |
| "image_token_embed": 4096, | |
| "image_token_size": 16384, | |
| "n_embed": 4096 | |
| } | |
| }, | |
| "gen_vision_config": { | |
| "cls": "VQ-16", | |
| "model_type": "gen_vision", | |
| "params": { | |
| "image_token_size": 16384, | |
| "n_embed": 8 | |
| } | |
| }, | |
| "language_config": { | |
| "_attn_implementation_autoset": true, | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 11008, | |
| "max_position_embeddings": 16384, | |
| "mlp_bias": false, | |
| "model_type": "llama", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 30, | |
| "num_key_value_heads": 32, | |
| "pretraining_tp": 1, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": null, | |
| "rope_theta": 10000.0, | |
| "torch_dtype": "bfloat16", | |
| "use_cache": true, | |
| "vocab_size": 102400 | |
| }, | |
| "model_type": "multi_modality", | |
| "pad_token_id": 100015, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.51.0", | |
| "vision_config": { | |
| "cls": "CLIPVisionTower", | |
| "model_type": "vision", | |
| "params": { | |
| "image_size": 384, | |
| "model_name": "siglip_large_patch16_384", | |
| "select_feature": "same", | |
| "select_layer": -1 | |
| } | |
| } | |
| } | |