| { | |
| "_name_or_path": "final-hf/paligemma-3b-pt-224-main", | |
| "architectures": [ | |
| "PaliGemmaForConditionalGeneration" | |
| ], | |
| "bos_token_id": 2, | |
| "eos_token_id": 1, | |
| "hidden_size": 2048, | |
| "ignore_index": -100, | |
| "image_token_index": 257152, | |
| "model_type": "paligemma", | |
| "pad_token_id": 0, | |
| "projection_dim": 2048, | |
| "text_config": { | |
| "hidden_size": 2048, | |
| "intermediate_size": 16384, | |
| "model_type": "gemma", | |
| "num_attention_heads": 8, | |
| "num_hidden_layers": 18, | |
| "num_image_tokens": 256, | |
| "num_key_value_heads": 1, | |
| "torch_dtype": "float32", | |
| "vocab_size": 257216 | |
| }, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.41.0.dev0", | |
| "vision_config": { | |
| "hidden_size": 1152, | |
| "intermediate_size": 4304, | |
| "model_type": "siglip_vision_model", | |
| "num_attention_heads": 16, | |
| "num_hidden_layers": 27, | |
| "num_image_tokens": 256, | |
| "patch_size": 14, | |
| "projection_dim": 2048, | |
| "projector_hidden_act": "gelu_fast", | |
| "vision_use_head": false | |
| }, | |
| "vocab_size": 257216, | |
| "model": { | |
| "llm_backbone_id": "gemma-2b", | |
| "llm_max_length": 2048, | |
| "model_id": "paligemma-224px+3b", | |
| "type": "paligemma-224px+3b", | |
| "vision_backbone_id": "siglip-vit-so400m", | |
| "arch_specifier": "linear", | |
| "image_resize_strategy": "resize-naive", | |
| "reduce_in_full_precision": false, | |
| "align_epochs": 1, | |
| "align_global_batch_size": 256, | |
| "align_learning_rate": 0.001, | |
| "align_lr_scheduler_type": "linear-warmup+cosine-decay", | |
| "align_max_grad_norm": 1.0, | |
| "align_max_steps": null, | |
| "align_per_device_batch_size": 16, | |
| "align_train_strategy": "fsdp-shard-grad-op", | |
| "align_warmup_ratio": 0.03, | |
| "align_weight_decay": 0.0, | |
| "enable_gradient_checkpointing": true, | |
| "enable_mixed_precision_training": true | |
| } | |
| } | |