| { | |
| "architectures": [ | |
| "LlavaOnevisionForConditionalGeneration" | |
| ], | |
| "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_token_index": 100352, | |
| "model_type": "llava_onevision", | |
| "multimodal_projector_bias": true, | |
| "num_image_tokens": 6551, | |
| "projector_hidden_act": "gelu", | |
| "text_config": { | |
| "_name_or_path": "stockmark/Stockmark-2-100B-Instruct-beta", | |
| "architectures": [ | |
| "LlamaForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 0, | |
| "eos_token_id": 1, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 9216, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 32768, | |
| "max_position_embeddings": 32768, | |
| "mlp_bias": false, | |
| "model_type": "llama", | |
| "num_attention_heads": 72, | |
| "num_hidden_layers": 86, | |
| "num_key_value_heads": 8, | |
| "pad_token_id": 2, | |
| "pretraining_tp": 1, | |
| "rms_norm_eps": 1e-05, | |
| "rope_scaling": null, | |
| "rope_theta": 10000.0, | |
| "torch_dtype": "bfloat16", | |
| "use_cache": true, | |
| "vocab_size": 100416 | |
| }, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.51.3", | |
| "use_image_newline_parameter": true, | |
| "video_token_index": 100353, | |
| "vision_aspect_ratio": "anyres_max_9", | |
| "vision_config": { | |
| "attention_dropout": 0.0, | |
| "hidden_act": "gelu_pytorch_tanh", | |
| "hidden_size": 1152, | |
| "image_size": 384, | |
| "intermediate_size": 4304, | |
| "layer_norm_eps": 1e-06, | |
| "model_type": "siglip_vision_model", | |
| "num_attention_heads": 16, | |
| "num_channels": 3, | |
| "num_hidden_layers": 26, | |
| "patch_size": 14, | |
| "vision_use_head": false | |
| }, | |
| "vision_feature_layer": -1, | |
| "vision_feature_select_strategy": "full" | |
| } | |