| { | |
| "architectures": [ | |
| "DeepseekVLHybridForConditionalGeneration" | |
| ], | |
| "high_res_vision_config": { | |
| "attention_dropout": 0.0, | |
| "global_attn_indexes": [ | |
| 2, | |
| 5, | |
| 8, | |
| 11 | |
| ], | |
| "hidden_act": "gelu", | |
| "hidden_size": 768, | |
| "image_size": 1024, | |
| "initializer_range": 1e-10, | |
| "intermediate_size": 3072, | |
| "layer_norm_eps": 1e-06, | |
| "mlp_dim": 3072, | |
| "mlp_ratio": 4.0, | |
| "model_type": "sam_vision_model", | |
| "num_attention_heads": 12, | |
| "num_channels": 3, | |
| "num_hidden_layers": 12, | |
| "num_pos_feats": 128, | |
| "output_channels": 256, | |
| "patch_size": 16, | |
| "qkv_bias": true, | |
| "use_abs_pos": true, | |
| "use_rel_pos": true, | |
| "window_size": 14 | |
| }, | |
| "image_token_id": 100015, | |
| "model_type": "deepseek_vl_hybrid", | |
| "text_config": { | |
| "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, | |
| "use_cache": true, | |
| "vocab_size": 102400 | |
| }, | |
| "torch_dtype": "float16", | |
| "transformers_version": "4.53.0.dev0", | |
| "vision_config": { | |
| "attention_dropout": 0.0, | |
| "hidden_act": "gelu", | |
| "hidden_size": 1024, | |
| "image_size": 384, | |
| "intermediate_size": 4096, | |
| "layer_norm_eps": 1e-06, | |
| "model_type": "siglip_vision_model", | |
| "num_attention_heads": 16, | |
| "num_channels": 3, | |
| "num_hidden_layers": 24, | |
| "patch_size": 16, | |
| "vision_use_head": false | |
| } | |
| } | |