| { |
| "architectures": [ |
| "LlavaForConditionalGeneration" |
| ], |
| "dtype": "float32", |
| "ignore_index": -100, |
| "image_seq_length": 576, |
| "image_token_index": 32000, |
| "model_type": "llava", |
| "multimodal_projector_bias": true, |
| "pad_token_id": 32001, |
| "projector_hidden_act": "gelu", |
| "text_config": { |
| "_name_or_path": "lmsys/vicuna-7b-v1.5", |
| "architectures": [ |
| "LlamaForCausalLM" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "dtype": "float16", |
| "head_dim": 128, |
| "hidden_act": "silu", |
| "hidden_size": 16, |
| "initializer_range": 0.02, |
| "intermediate_size": 11008, |
| "layer_types": null, |
| "max_position_embeddings": 4096, |
| "mlp_bias": false, |
| "model_type": "llama", |
| "num_attention_heads": 4, |
| "num_hidden_layers": 2, |
| "num_key_value_heads": 2, |
| "pretraining_tp": 1, |
| "rms_norm_eps": 1e-05, |
| "rope_parameters": { |
| "rope_theta": 10000.0, |
| "rope_type": "default" |
| }, |
| "use_cache": true, |
| "vocab_size": 32064 |
| }, |
| "tie_word_embeddings": false, |
| "transformers_version": "5.0.0.dev0", |
| "vision_config": { |
| "attention_dropout": 0.0, |
| "embed_dim": 64, |
| "hidden_act": "quick_gelu", |
| "hidden_size": 16, |
| "image_size": 336, |
| "initializer_factor": 1.0, |
| "initializer_range": 0.02, |
| "intermediate_size": 4096, |
| "layer_norm_eps": 1e-05, |
| "model_type": "clip_vision_model", |
| "num_attention_heads": 4, |
| "num_channels": 3, |
| "num_hidden_layers": 2, |
| "num_key_value_heads": 2, |
| "patch_size": 14, |
| "projection_dim": 768, |
| "vocab_size": 32000 |
| }, |
| "vision_feature_layer": -2, |
| "vision_feature_select_strategy": "default", |
| "vocab_size": 32064 |
| } |
|
|