Image-Text-to-Text
Transformers
Safetensors
English
qwen3_vl
image-to-text
programming
code generation
images
image to text
qwen3_vl_text
Qwen3VLForConditionalGeneration
thinking
reasoning
video
code
coding
coder
chat
brainstorm
qwen
qwen3
qwencoder
brainstorm 20x
all uses cases
finetune
conversational
| { | |
| "architectures": [ | |
| "Qwen3VLForConditionalGeneration" | |
| ], | |
| "dtype": "bfloat16", | |
| "image_token_id": 151655, | |
| "model_type": "qwen3_vl", | |
| "text_config": { | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 151643, | |
| "dtype": "bfloat16", | |
| "eos_token_id": 151645, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 12288, | |
| "max_position_embeddings": 262144, | |
| "model_type": "qwen3_vl_text", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 55, | |
| "num_key_value_heads": 8, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": { | |
| "mrope_interleaved": true, | |
| "mrope_section": [ | |
| 24, | |
| 20, | |
| 20 | |
| ], | |
| "rope_type": "default" | |
| }, | |
| "rope_theta": 5000000, | |
| "use_cache": true, | |
| "vocab_size": 151936 | |
| }, | |
| "tie_word_embeddings": false, | |
| "transformers_version": "5.0.0.dev0", | |
| "video_token_id": 151656, | |
| "vision_config": { | |
| "deepstack_visual_indexes": [ | |
| 8, | |
| 16, | |
| 24 | |
| ], | |
| "depth": 27, | |
| "hidden_act": "gelu_pytorch_tanh", | |
| "hidden_size": 1152, | |
| "in_channels": 3, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 4304, | |
| "model_type": "qwen3_vl", | |
| "num_heads": 16, | |
| "num_position_embeddings": 2304, | |
| "out_hidden_size": 4096, | |
| "patch_size": 16, | |
| "spatial_merge_size": 2, | |
| "temporal_patch_size": 2 | |
| }, | |
| "vision_end_token_id": 151653, | |
| "vision_start_token_id": 151652 | |
| } | |