| { | |
| "architectures": [ | |
| "InternVLForConditionalGeneration" | |
| ], | |
| "downsample_ratio": 0.5, | |
| "image_seq_length": 256, | |
| "image_token_index": 92546, | |
| "model_type": "internvl", | |
| "projector_hidden_act": "gelu", | |
| "text_config": { | |
| "_attn_implementation_autoset": true, | |
| "architectures": [ | |
| "InternLM2ForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "bos_token_id": 1, | |
| "eos_token_id": 2, | |
| "head_dim": 128, | |
| "hidden_size": 4096, | |
| "intermediate_size": 14336, | |
| "max_position_embeddings": 32768, | |
| "mlp_bias": false, | |
| "model_type": "llama", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 32, | |
| "num_key_value_heads": 8, | |
| "pad_token_id": 2, | |
| "pretraining_tp": 1, | |
| "rms_norm_eps": 1e-05, | |
| "rope_scaling": { | |
| "factor": 2.0, | |
| "rope_type": "dynamic", | |
| "type": "dynamic" | |
| }, | |
| "rope_theta": 1000000, | |
| "torch_dtype": "bfloat16", | |
| "vocab_size": 92553 | |
| }, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.50.0.dev0", | |
| "vision_config": { | |
| "_attn_implementation_autoset": true, | |
| "architectures": [ | |
| "InternVisionModel" | |
| ], | |
| "attention_dropout": 0.0, | |
| "drop_path_rate": 0.0, | |
| "dropout": 0.0, | |
| "initializer_factor": 1.0, | |
| "layer_scale_init_value": 0.1, | |
| "model_type": "internvl_vision", | |
| "torch_dtype": "bfloat16" | |
| }, | |
| "vision_feature_layer": -1 | |
| } | |