| { |
| "architectures": [ |
| "CompoDistillForConditionalGeneration" |
| ], |
| "auto_map": { |
| "AutoConfig": "configuration_compodistill.CompoDistillConfig", |
| "AutoModelForCausalLM": "modeling_compodistill.CompoDistillForConditionalGeneration" |
| }, |
| "cache_dir": null, |
| "connector_hidden_size": null, |
| "connector_type": "mlp2x_gelu", |
| "hidden_size": 2048, |
| "ignore_index": -100, |
| "image_aspect_ratio": "square", |
| "image_token_index": -200, |
| "llm_model_name_or_path": "Qwen/Qwen1.5-1.8B", |
| "model_type": "compodistill", |
| "num_queries": 128, |
| "num_resampler_layers": 3, |
| "pad_token": null, |
| "post_connector_use": false, |
| "resampler_hidden_size": 768, |
| "text_config": { |
| "_attn_implementation_autoset": true, |
| "_name_or_path": "Qwen/Qwen1.5-1.8B", |
| "architectures": [ |
| "Qwen2ForCausalLM" |
| ], |
| "attention_dropout": 0.0, |
| "bos_token_id": 151643, |
| "eos_token_id": 151643, |
| "hidden_act": "silu", |
| "hidden_size": 2048, |
| "initializer_range": 0.02, |
| "intermediate_size": 5504, |
| "max_position_embeddings": 32768, |
| "max_window_layers": 21, |
| "model_type": "qwen2", |
| "num_attention_heads": 16, |
| "num_hidden_layers": 24, |
| "num_key_value_heads": 16, |
| "rms_norm_eps": 1e-06, |
| "rope_scaling": null, |
| "rope_theta": 1000000.0, |
| "sliding_window": 32768, |
| "torch_dtype": "float16", |
| "use_cache": true, |
| "use_sliding_window": false, |
| "vocab_size": 151936 |
| }, |
| "tokenizer_model_max_length": 2048, |
| "tokenizer_name_or_path": "Qwen/Qwen1.5-1.8B", |
| "tokenizer_padding_side": "right", |
| "tokenizer_use_fast": false, |
| "torch_dtype": "float16", |
| "transformers_version": "4.50.0.dev0", |
| "tune_type_connector": "full", |
| "tune_type_llm": "lora", |
| "tune_type_vision_tower": "frozen", |
| "tune_vision_tower_from_layer": 0, |
| "use_cache": true, |
| "vision_config": { |
| "_attn_implementation_autoset": true, |
| "attention_dropout": 0.0, |
| "hidden_act": "gelu_pytorch_tanh", |
| "hidden_size": 1152, |
| "image_size": 384, |
| "intermediate_size": 4304, |
| "layer_norm_eps": 1e-06, |
| "model_name_or_path": "google/siglip-so400m-patch14-384", |
| "model_name_or_path2": "", |
| "model_type": "siglip_vision_model", |
| "num_attention_heads": 16, |
| "num_channels": 3, |
| "num_hidden_layers": 27, |
| "patch_size": 14 |
| }, |
| "vision_feature_layer": -2, |
| "vision_feature_select_strategy": "patch", |
| "vision_hidden_size": 1152, |
| "vision_model_name_or_path": "google/siglip-so400m-patch14-384", |
| "vision_model_name_or_path2": "", |
| "vocab_size": 151936 |
| } |
|
|
