{
"model_id": "qwen2vl",
"img_context_token_id": 151655,
"image_encoder": {
"vision_encoder": {
"model_id": "qwen2vit",
"num_layers": 32,
"hidden_size": 1280,
"ffn_hidden_size": 5120,
"llm_hidden_size": 3584,
"num_attention_heads": 16,
"hidden_dropout": 0.0,
"attention_dropout": 0.0,
"in_channels": 3,
"patch_size": 14,
"spatial_merge_size": 2,
"temporal_patch_size": 2,
"layernorm_epsilon": 1e-06,
"normalization": "LayerNorm",
"fp16": false,
"bf16": true,
"params_dtype": "bf16",
"activation_func": "quick_gelu",
"freeze": true,
"use_fused_rotary_pos_emb": true,
"post_layer_norm": false,
"pipeline_num_layers": [32, 0, 0, 0]
},
"vision_projector": {
"model_id": "lnmlp",
"num_layers": 1,
"gated_linear_unit": false,
"bias_activation_fusion": false,
"add_bias_linear": true,
"input_size": 1280,
"hidden_size": 3584,
"ffn_hidden_size": 5120,
"activation_func": "gelu",
"bf16": true,
"params_dtype": "bf16",
"freeze": true,
"layernorm_epsilon": 1e-06,
"normalization": "LayerNorm"
}
},
"text_decoder": {
"model_id": "qwen2lm",
"num_layers": 28,
"pipeline_num_layers": [1, 10, 10, 7],
"hidden_size": 3584,
"ffn_hidden_size": 18944,
"num_attention_heads": 28,
"max_position_embeddings": 32768,
"vocab_size": 152064,
"rope_theta": 1000000.0,
"untie_embeddings_and_output_weights": true,
"disable_bias_linear": true,
"attention_dropout": 0.0,
"init_method_std": 0.01,
"hidden_dropout": 0.0,
"position_embedding_type": "mrope",
"normalization": "RMSNorm",
"activation_func": "silu",
"use_fused_rotary_pos_emb": true,
"attention_softmax_in_fp32": true,
"params_dtype": "bf16",
"bf16": true,
"parallel_output": true,
"group_query_attention": true,
"num_query_groups": 4,
"mrope_section": [16, 24, 24],
"rope_scaling": null,
"gated_linear_unit": true,
"layernorm_epsilon": 1e-06,
"add_bias_linear":false,
"add_qkv_bias": true
},
"text_encoder": null,
"video_encoder": null
}