| { |
| "architectures": [ |
| "XGenMMModelForConditionalGeneration" |
| ], |
| "auto_map": { |
| "AutoConfig": "configuration_xgenmm.XGenMMConfig", |
| "AutoModelForVision2Seq": "modeling_xgenmm.XGenMMModelForConditionalGeneration" |
| }, |
| "model_type": "xgenmm", |
| "text_config": { |
| "initial_tokenizer_len": 32012, |
| "model_type": "phi3", |
| "sliding_window": 2047, |
| "torch_dtype": "bfloat16" |
| }, |
| "torch_dtype": "float32", |
| "transformers_version": "4.41.0.dev0", |
| "vision_encoder_config": { |
| "anyres_patch_sampling": false, |
| "image_aspect_ratio": "pad", |
| "model_type": "xgenmm_vision_encoder" |
| }, |
| "vision_tokenizer_config": { |
| "model_type": "xgenmm_vision_tokenizer" |
| } |
| } |
|
|