{ "_name_or_path": "mylesgoose/Llama-3.1-Minitron-4B-Width-Base", "add_faster_video": false, "add_time_instruction": false, "architectures": [ "LlavaOnevisionForConditionalGeneration" ], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": [ 128001, 128008, 128009 ], "faster_token_stride": 10, "force_sample": false, "head_dim": 128, "hidden_act": "silu", "hidden_size": 3072, "image_aspect_ratio": "anyres_max_9", "image_crop_resolution": null, "image_grid_pinpoints": [ [ 384, 384 ], [ 384, 768 ], [ 384, 1152 ], [ 384, 1536 ], [ 384, 1920 ], [ 384, 2304 ], [ 768, 384 ], [ 768, 768 ], [ 768, 1152 ], [ 768, 1536 ], [ 768, 1920 ], [ 768, 2304 ], [ 1152, 384 ], [ 1152, 768 ], [ 1152, 1152 ], [ 1152, 1536 ], [ 1152, 1920 ], [ 1152, 2304 ], [ 1536, 384 ], [ 1536, 768 ], [ 1536, 1152 ], [ 1536, 1536 ], [ 1536, 1920 ], [ 1536, 2304 ], [ 1920, 384 ], [ 1920, 768 ], [ 1920, 1152 ], [ 1920, 1536 ], [ 1920, 1920 ], [ 1920, 2304 ], [ 2304, 384 ], [ 2304, 768 ], [ 2304, 1152 ], [ 2304, 1536 ], [ 2304, 1920 ], [ 2304, 2304 ] ], "image_split_resolution": null, "initializer_range": 0.02, "intermediate_size": 9216, "max_position_embeddings": 131072, "mlp_bias": false, "mm_hidden_size": 1152, "mm_newline_position": "grid", "mm_patch_merge_type": "spatial_unpad", "mm_projector_lr": null, "mm_projector_type": "mlp2x_gelu", "mm_resampler_type": null, "mm_spatial_pool_mode": "bilinear", "mm_spatial_pool_stride": null, "mm_tunable_parts": "mm_vision_tower,mm_mlp_adapter,mm_language_model", "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": "google/siglip-so400m-patch14-384", "mm_vision_tower_lr": 2e-06, "model_type": "llama", "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "pad_token_id": 128004, "pos_skipping_range": 4096, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": { "factor": 8.0, "high_freq_factor": 4.0, "low_freq_factor": 1.0, "original_max_position_embeddings": 8192, "rope_type": "llama3" }, "rope_theta": 500000.0, "tie_word_embeddings": false, "tokenizer_model_max_length": 131072, "tokenizer_padding_side": "right", "torch_dtype": "bfloat16", "transformers_version": "4.45.0.dev0", "use_cache": false, "use_mm_proj": true, "use_pos_skipping": false, "vision_tower_pretrained": null, "vocab_size": 128256, "vision_config": { "hidden_size": 1152, "image_size": 384, "intermediate_size": 4304, "model_type": "siglip_vision_model", "num_attention_heads": 32, "num_hidden_layers": 26, "patch_size": 14, "vision_use_head": false }, "vision_feature_layer": -2, "vision_feature_select_strategy": "full" }