| { |
| "architectures": [ |
| "TinyLlavaForConditionalGeneration" |
| ], |
| "auto_map": { |
| "AutoConfig": "configuration_tinyllava.TinyLlavaConfig", |
| "AutoModelForCausalLM": "modeling_tinyllava.TinyLlavaForConditionalGeneration" |
| }, |
| "cache_dir": null, |
| "connector_type": "mlp2x_gelu", |
| "hidden_size": 4096, |
| "ignore_index": -100, |
| "image_aspect_ratio": "square", |
| "image_token_index": -200, |
| "llm_model_name_or_path": "Qwen/Qwen3-8B", |
| "model_type": "tinyllava", |
| "num_queries": 128, |
| "num_resampler_layers": 3, |
| "pad_token": "<|endoftext|>", |
| "resampler_hidden_size": 768, |
| "text_config": { |
| "_attn_implementation_autoset": true, |
| "_name_or_path": "Qwen/Qwen3-8B", |
| "architectures": [ |
| "Qwen3ForCausalLM" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "bos_token_id": 151643, |
| "eos_token_id": 151645, |
| "head_dim": 128, |
| "hidden_act": "silu", |
| "hidden_size": 4096, |
| "initializer_range": 0.02, |
| "intermediate_size": 12288, |
| "max_position_embeddings": 40960, |
| "max_window_layers": 36, |
| "model_type": "qwen3", |
| "num_attention_heads": 32, |
| "num_hidden_layers": 36, |
| "num_key_value_heads": 8, |
| "rms_norm_eps": 1e-06, |
| "rope_scaling": null, |
| "rope_theta": 1000000, |
| "sliding_window": null, |
| "torch_dtype": "bfloat16", |
| "use_cache": true, |
| "use_sliding_window": false, |
| "vocab_size": 151936 |
| }, |
| "tokenizer_model_max_length": 2048, |
| "tokenizer_name_or_path": "Qwen/Qwen3-8B", |
| "tokenizer_padding_side": "right", |
| "tokenizer_use_fast": false, |
| "torch_dtype": "float32", |
| "transformers_version": "4.51.3", |
| "tune_type_connector": "full", |
| "tune_type_llm": "full", |
| "tune_type_vision_tower": "frozen", |
| "tune_vision_tower_from_layer": 0, |
| "use_cache": true, |
| "vision_config": { |
| "_attn_implementation_autoset": true, |
| "attention_dropout": 0.0, |
| "dropout": 0.0, |
| "hidden_act": "quick_gelu", |
| "hidden_size": 1024, |
| "image_size": 336, |
| "initializer_factor": 1.0, |
| "initializer_range": 0.02, |
| "intermediate_size": 4096, |
| "layer_norm_eps": 1e-05, |
| "model_name_or_path": "openai/clip-vit-large-patch14-336", |
| "model_name_or_path2": "", |
| "model_type": "clip_vision_model", |
| "num_attention_heads": 16, |
| "num_channels": 3, |
| "num_hidden_layers": 24, |
| "patch_size": 14, |
| "projection_dim": 768 |
| }, |
| "vision_feature_layer": -2, |
| "vision_feature_select_strategy": "patch", |
| "vision_hidden_size": 1024, |
| "vision_model_name_or_path": "openai/clip-vit-large-patch14-336", |
| "vision_model_name_or_path2": "", |
| "vocab_size": 151936 |
| } |
|
|
