| { | |
| "architectures": [ | |
| "LlavaForConditionalGeneration" | |
| ], | |
| "bos_token_id": 1, | |
| "torch_dtype": "bfloat16", | |
| "eos_token_id": 2, | |
| "ignore_index": -100, | |
| "image_seq_length": 1, | |
| "image_token_index": 10, | |
| "model_type": "llava", | |
| "multimodal_projector_bias": true, | |
| "pad_token_id": 11, | |
| "projector_hidden_act": "gelu", | |
| "text_config": { | |
| "_attn_implementation_autoset": false, | |
| "attention_dropout": 0.0, | |
| "torch_dtype": "bfloat16", | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 5120, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 14336, | |
| "max_position_embeddings": 262400, | |
| "model_type": "mistral", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 48, | |
| "num_key_value_heads": 8, | |
| "rms_norm_eps": 1e-05, | |
| "rope_theta": 1000000000.0, | |
| "sliding_window": null, | |
| "use_cache": true, | |
| "vocab_size": 131072 | |
| }, | |
| "transformers_version": "4.56.2", | |
| "unsloth_fixed": true, | |
| "vision_config": { | |
| "_attn_implementation_autoset": false, | |
| "attention_dropout": 0.0, | |
| "torch_dtype": "bfloat16", | |
| "head_dim": 64, | |
| "hidden_act": "silu", | |
| "hidden_size": 1024, | |
| "image_size": 1024, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 4096, | |
| "model_type": "pixtral", | |
| "num_attention_heads": 16, | |
| "num_channels": 3, | |
| "num_hidden_layers": 24, | |
| "patch_size": 16, | |
| "rope_theta": 10000.0 | |
| }, | |
| "vision_feature_layer": -1, | |
| "vision_feature_select_strategy": "full" | |
| } | |