| { | |
| "auto_map": { | |
| "AutoConfig": "configuration_mobilevlm.MobileVLMConfig" | |
| }, | |
| "freeze_mm_mlp_adapter": false, | |
| "hidden_act": "silu", | |
| "hidden_size": 2048, | |
| "image_aspect_ratio": "pad", | |
| "image_grid_pinpoints": null, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 5632, | |
| "max_position_embeddings": 2048, | |
| "max_sequence_length": 2048, | |
| "mm_hidden_size": 1024, | |
| "mm_projector_type": "ldpnet", | |
| "mm_use_im_patch_token": false, | |
| "mm_use_im_start_end": false, | |
| "mm_vision_select_feature": "patch", | |
| "mm_vision_select_layer": -2, | |
| "mm_vision_tower": "openai/clip-vit-large-patch14-336", | |
| "model_type": "mobilevlm", | |
| "num_attention_heads": 16, | |
| "num_hidden_layers": 24, | |
| "num_key_value_heads": 16, | |
| "pretraining_tp": 1, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": null, | |
| "rope_theta": 10000.0, | |
| "transformers_version": "4.37.2", | |
| "tune_mm_mlp_adapter": false, | |
| "use_cache": true, | |
| "use_mm_proj": true, | |
| "vision_tower_type": "clip", | |
| "vocab_size": 32000 | |
| } | |