|
{ |
|
"_attn_implementation_autoset": true, |
|
"_name_or_path": "Qwen/Qwen2-VL-2B-Instruct", |
|
"architectures": [ |
|
"Qwen2VLForConditionalGeneration" |
|
], |
|
"attention_dropout": 0.0, |
|
"bos_token_id": 151643, |
|
"eos_token_id": 151645, |
|
"hidden_act": "silu", |
|
"hidden_size": 1536, |
|
"image_token_id": 151655, |
|
"initializer_range": 0.02, |
|
"intermediate_size": 8960, |
|
"max_position_embeddings": 32768, |
|
"max_window_layers": 28, |
|
"model_type": "qwen2_vl", |
|
"num_attention_heads": 12, |
|
"num_hidden_layers": 28, |
|
"num_key_value_heads": 2, |
|
"rms_norm_eps": 1e-06, |
|
"rope_scaling": { |
|
"mrope_section": [ |
|
16, |
|
24, |
|
24 |
|
], |
|
"rope_type": "default", |
|
"type": "default" |
|
}, |
|
"rope_theta": 1000000.0, |
|
"sliding_window": 32768, |
|
"tie_word_embeddings": true, |
|
"torch_dtype": "bfloat16", |
|
"transformers_version": "4.46.1", |
|
"transformers.js_config": { |
|
"dtype": { |
|
"vision_encoder": "q8", |
|
"embed_tokens": "fp16", |
|
"decoder_model_merged": "q4" |
|
} |
|
}, |
|
"use_cache": true, |
|
"use_sliding_window": false, |
|
"video_token_id": 151656, |
|
"vision_config": { |
|
"hidden_size": 1536, |
|
"in_chans": 3, |
|
"model_type": "qwen2_vl", |
|
"spatial_patch_size": 14 |
|
}, |
|
"vision_end_token_id": 151653, |
|
"vision_start_token_id": 151652, |
|
"vision_token_id": 151654, |
|
"vocab_size": 151936 |
|
} |
|
|