{ "architectures": [ "InternVLForConditionalGeneration" ], "downsample_ratio": 0.5, "image_seq_length": 256, "image_token_id": 200021, "model_type": "internvl", "projector_hidden_act": "gelu", "text_config": { "_name_or_path": "/mnt/shared-storage-user/intern7shared/internvl_a4s/checkpoints/gpt-oss-20b", "architectures": [ "GptOssForCausalLM" ], "attention_bias": true, "attention_dropout": 0.0, "eos_token_id": 200002, "experts_per_token": 4, "head_dim": 64, "hidden_act": "silu", "hidden_size": 2880, "initial_context_length": 4096, "initializer_range": 0.02, "intermediate_size": 2880, "layer_types": [ "sliding_attention", "full_attention", "sliding_attention", "full_attention", "sliding_attention", "full_attention", "sliding_attention", "full_attention", "sliding_attention", "full_attention", "sliding_attention", "full_attention", "sliding_attention", "full_attention", "sliding_attention", "full_attention", "sliding_attention", "full_attention", "sliding_attention", "full_attention", "sliding_attention", "full_attention", "sliding_attention", "full_attention" ], "max_position_embeddings": 131072, "model_type": "gpt_oss", "num_attention_heads": 64, "num_experts_per_tok": 4, "num_hidden_layers": 24, "num_key_value_heads": 8, "num_local_experts": 32, "output_router_logits": false, "pad_token_id": 199999, "rms_norm_eps": 1e-05, "rope_scaling": { "beta_fast": 32.0, "beta_slow": 1.0, "factor": 32.0, "original_max_position_embeddings": 4096, "rope_type": "yarn", "truncate": false }, "rope_theta": 150000, "router_aux_loss_coef": 0.9, "sliding_window": 128, "swiglu_limit": 7.0, "use_cache": true, "vocab_size": 200028 }, "torch_dtype": "bfloat16", "transformers_version": "4.55.0", "vision_config": { "architectures": [ "InternVisionModel" ], "attention_bias": true, "attention_dropout": 0.0, "dropout": 0.0, "hidden_act": "gelu", "hidden_dropout_prob": 0.0, "hidden_size": 1024, "image_size": [ 448, 448 ], "initializer_factor": 0.1, "initializer_range": 1e-10, "intermediate_size": 4096, "layer_norm_eps": 1e-06, "layer_scale_init_value": 0.1, "model_type": "internvl_vision", "norm_type": "layer_norm", "num_attention_heads": 16, "num_channels": 3, "num_hidden_layers": 24, "patch_size": [ 14, 14 ], "projection_dropout": 0.0, "torch_dtype": "bfloat16", "use_absolute_position_embeddings": true, "use_mask_token": false, "use_mean_pooling": true, "use_qk_norm": false }, "vision_feature_layer": -1, "vision_feature_select_strategy": "default" }