| { | |
| "architectures": [ | |
| "VideoMllamaForConditionalGeneration" | |
| ], | |
| "model_type": "mllama", | |
| "auto_map": { | |
| "AutoConfig": "configuration_video_mllama.VideoMllamaConfig", | |
| "AutoModelForCausalLM": "modeling_video_mllama.VideoMllamaForConditionalGeneration", | |
| "AutoModel": "modeling_video_mllama.VideoMllamaForConditionalGeneration", | |
| "AutoProcessor": "processing_video_mllama.VideoMllamaProcessor" | |
| }, | |
| "image_token_index": 128256, | |
| "hidden_size": 4096, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.47.1", | |
| "use_cache": false, | |
| "text_config": { | |
| "model_type": "video_mllama_text_model", | |
| "rope_scaling": { | |
| "factor": 8.0, | |
| "high_freq_factor": 4.0, | |
| "low_freq_factor": 1.0, | |
| "original_max_position_embeddings": 8192, | |
| "rope_type": "llama3" | |
| }, | |
| "torch_dtype": "bfloat16", | |
| "eos_token_id": [ | |
| 128001, | |
| 128008, | |
| 128009 | |
| ] | |
| }, | |
| "vision_config": { | |
| "model_type": "video_mllama_vision_model", | |
| "image_size": 560, | |
| "torch_dtype": "bfloat16" | |
| } | |
| } | |