| { |
| "architectures": [ |
| "Qwen2_5_VLForConditionalGeneration" |
| ], |
| "attention_dropout": 0.0, |
| "bos_token_id": 151643, |
| "dtype": "bfloat16", |
| "eos_token_id": 151645, |
| "head_dim": 128, |
| "hidden_act": "silu", |
| "hidden_size": 1024, |
| "image_token_id": 151655, |
| "initializer_range": 0.02, |
| "intermediate_size": 3072, |
| "max_position_embeddings": 128000, |
| "max_window_layers": 28, |
| "model_type": "qwen2_5_vl", |
| "num_attention_heads": 16, |
| "num_hidden_layers": 28, |
| "num_key_value_heads": 8, |
| "rms_norm_eps": 1e-06, |
| "rope_scaling": { |
| "mrope_section": [ |
| 16, |
| 24, |
| 24 |
| ], |
| "rope_type": "default", |
| "type": "default" |
| }, |
| "rope_theta": 1000000.0, |
| "sliding_window": 32768, |
| "text_config": { |
| "_name_or_path": "", |
| "architectures": [ |
| "Qwen2_5_VLForConditionalGeneration" |
| ], |
| "attention_dropout": 0.0, |
| "dtype": "bfloat16", |
| "eos_token_id": 151645, |
| "head_dim": 128, |
| "hidden_act": "silu", |
| "hidden_size": 1024, |
| "initializer_range": 0.02, |
| "intermediate_size": 3072, |
| "layer_types": [ |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention" |
| ], |
| "max_position_embeddings": 128000, |
| "max_window_layers": 28, |
| "model_type": "qwen2_5_vl_text", |
| "num_attention_heads": 16, |
| "num_hidden_layers": 28, |
| "num_key_value_heads": 8, |
| "pad_token_id": 151643, |
| "rms_norm_eps": 1e-06, |
| "rope_scaling": { |
| "mrope_section": [ |
| 16, |
| 24, |
| 24 |
| ], |
| "rope_type": "default", |
| "type": "default" |
| }, |
| "rope_theta": 1000000.0, |
| "sliding_window": null, |
| "tie_word_embeddings": true, |
| "use_cache": false, |
| "use_sliding_window": false, |
| "vision_token_id": 151654, |
| "vocab_size": 151936 |
| }, |
| "transformers_version": "4.57.1", |
| "use_cache": true, |
| "use_sliding_window": false, |
| "video_token_id": 151656, |
| "vision_config": { |
| "depth": 32, |
| "dtype": "bfloat16", |
| "fullatt_block_indexes": [ |
| 7, |
| 15, |
| 23, |
| 31 |
| ], |
| "hidden_act": "silu", |
| "hidden_size": 1280, |
| "in_channels": 3, |
| "in_chans": 3, |
| "initializer_range": 0.02, |
| "intermediate_size": 3420, |
| "model_type": "qwen2_5_vl", |
| "num_heads": 16, |
| "out_hidden_size": 1024, |
| "pad_token_id": 151643, |
| "patch_size": 14, |
| "spatial_merge_size": 2, |
| "spatial_patch_size": 14, |
| "temporal_patch_size": 2, |
| "tokens_per_second": 2, |
| "window_size": 112 |
| }, |
| "vision_end_token_id": 151653, |
| "vision_start_token_id": 151652, |
| "vision_token_id": 151654, |
| "vocab_size": 151936, |
| "transformers.js_config": { |
| "use_external_data_format": { |
| "decoder_model_merged.onnx": 2, |
| "decoder_model_merged_fp16.onnx": 1, |
| "decoder_model_merged_q4f16.onnx": 1, |
| "embed_tokens.onnx": 1, |
| "embed_tokens_fp16.onnx": 1, |
| "embed_tokens_q4f16.onnx": 1, |
| "vision_encoder.onnx": 2, |
| "vision_encoder_fp16.onnx": 1, |
| "vision_encoder_q4f16.onnx": 1 |
| }, |
| "kv_cache_dtype": { |
| "fp16": "float16", |
| "q4f16": "float16" |
| } |
| } |
| } |
|
|
