Shubhra Pandit
Update model files
183210a
{
"_name_or_path": "Qwen/Qwen2.5-VL-3B-Instruct",
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 2048,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 11008,
"max_position_embeddings": 128000,
"max_window_layers": 70,
"model_type": "qwen2_5_vl",
"num_attention_heads": 16,
"num_hidden_layers": 36,
"num_key_value_heads": 2,
"quantization_config": {
"config_groups": {
"group_0": {
"input_activations": null,
"output_activations": null,
"targets": [
"Linear"
],
"weights": {
"actorder": "weight",
"block_structure": null,
"dynamic": false,
"group_size": 128,
"num_bits": 4,
"observer": "minmax",
"observer_kwargs": {},
"strategy": "group",
"symmetric": true,
"type": "int"
}
}
},
"format": "pack-quantized",
"global_compression_ratio": 1.3990843687790238,
"ignore": [
"visual.blocks.0.attn.qkv",
"visual.blocks.0.attn.proj",
"visual.blocks.0.mlp.gate_proj",
"visual.blocks.0.mlp.up_proj",
"visual.blocks.0.mlp.down_proj",
"visual.blocks.1.attn.qkv",
"visual.blocks.1.attn.proj",
"visual.blocks.1.mlp.gate_proj",
"visual.blocks.1.mlp.up_proj",
"visual.blocks.1.mlp.down_proj",
"visual.blocks.2.attn.qkv",
"visual.blocks.2.attn.proj",
"visual.blocks.2.mlp.gate_proj",
"visual.blocks.2.mlp.up_proj",
"visual.blocks.2.mlp.down_proj",
"visual.blocks.3.attn.qkv",
"visual.blocks.3.attn.proj",
"visual.blocks.3.mlp.gate_proj",
"visual.blocks.3.mlp.up_proj",
"visual.blocks.3.mlp.down_proj",
"visual.blocks.4.attn.qkv",
"visual.blocks.4.attn.proj",
"visual.blocks.4.mlp.gate_proj",
"visual.blocks.4.mlp.up_proj",
"visual.blocks.4.mlp.down_proj",
"visual.blocks.5.attn.qkv",
"visual.blocks.5.attn.proj",
"visual.blocks.5.mlp.gate_proj",
"visual.blocks.5.mlp.up_proj",
"visual.blocks.5.mlp.down_proj",
"visual.blocks.6.attn.qkv",
"visual.blocks.6.attn.proj",
"visual.blocks.6.mlp.gate_proj",
"visual.blocks.6.mlp.up_proj",
"visual.blocks.6.mlp.down_proj",
"visual.blocks.7.attn.qkv",
"visual.blocks.7.attn.proj",
"visual.blocks.7.mlp.gate_proj",
"visual.blocks.7.mlp.up_proj",
"visual.blocks.7.mlp.down_proj",
"visual.blocks.8.attn.qkv",
"visual.blocks.8.attn.proj",
"visual.blocks.8.mlp.gate_proj",
"visual.blocks.8.mlp.up_proj",
"visual.blocks.8.mlp.down_proj",
"visual.blocks.9.attn.qkv",
"visual.blocks.9.attn.proj",
"visual.blocks.9.mlp.gate_proj",
"visual.blocks.9.mlp.up_proj",
"visual.blocks.9.mlp.down_proj",
"visual.blocks.10.attn.qkv",
"visual.blocks.10.attn.proj",
"visual.blocks.10.mlp.gate_proj",
"visual.blocks.10.mlp.up_proj",
"visual.blocks.10.mlp.down_proj",
"visual.blocks.11.attn.qkv",
"visual.blocks.11.attn.proj",
"visual.blocks.11.mlp.gate_proj",
"visual.blocks.11.mlp.up_proj",
"visual.blocks.11.mlp.down_proj",
"visual.blocks.12.attn.qkv",
"visual.blocks.12.attn.proj",
"visual.blocks.12.mlp.gate_proj",
"visual.blocks.12.mlp.up_proj",
"visual.blocks.12.mlp.down_proj",
"visual.blocks.13.attn.qkv",
"visual.blocks.13.attn.proj",
"visual.blocks.13.mlp.gate_proj",
"visual.blocks.13.mlp.up_proj",
"visual.blocks.13.mlp.down_proj",
"visual.blocks.14.attn.qkv",
"visual.blocks.14.attn.proj",
"visual.blocks.14.mlp.gate_proj",
"visual.blocks.14.mlp.up_proj",
"visual.blocks.14.mlp.down_proj",
"visual.blocks.15.attn.qkv",
"visual.blocks.15.attn.proj",
"visual.blocks.15.mlp.gate_proj",
"visual.blocks.15.mlp.up_proj",
"visual.blocks.15.mlp.down_proj",
"visual.blocks.16.attn.qkv",
"visual.blocks.16.attn.proj",
"visual.blocks.16.mlp.gate_proj",
"visual.blocks.16.mlp.up_proj",
"visual.blocks.16.mlp.down_proj",
"visual.blocks.17.attn.qkv",
"visual.blocks.17.attn.proj",
"visual.blocks.17.mlp.gate_proj",
"visual.blocks.17.mlp.up_proj",
"visual.blocks.17.mlp.down_proj",
"visual.blocks.18.attn.qkv",
"visual.blocks.18.attn.proj",
"visual.blocks.18.mlp.gate_proj",
"visual.blocks.18.mlp.up_proj",
"visual.blocks.18.mlp.down_proj",
"visual.blocks.19.attn.qkv",
"visual.blocks.19.attn.proj",
"visual.blocks.19.mlp.gate_proj",
"visual.blocks.19.mlp.up_proj",
"visual.blocks.19.mlp.down_proj",
"visual.blocks.20.attn.qkv",
"visual.blocks.20.attn.proj",
"visual.blocks.20.mlp.gate_proj",
"visual.blocks.20.mlp.up_proj",
"visual.blocks.20.mlp.down_proj",
"visual.blocks.21.attn.qkv",
"visual.blocks.21.attn.proj",
"visual.blocks.21.mlp.gate_proj",
"visual.blocks.21.mlp.up_proj",
"visual.blocks.21.mlp.down_proj",
"visual.blocks.22.attn.qkv",
"visual.blocks.22.attn.proj",
"visual.blocks.22.mlp.gate_proj",
"visual.blocks.22.mlp.up_proj",
"visual.blocks.22.mlp.down_proj",
"visual.blocks.23.attn.qkv",
"visual.blocks.23.attn.proj",
"visual.blocks.23.mlp.gate_proj",
"visual.blocks.23.mlp.up_proj",
"visual.blocks.23.mlp.down_proj",
"visual.blocks.24.attn.qkv",
"visual.blocks.24.attn.proj",
"visual.blocks.24.mlp.gate_proj",
"visual.blocks.24.mlp.up_proj",
"visual.blocks.24.mlp.down_proj",
"visual.blocks.25.attn.qkv",
"visual.blocks.25.attn.proj",
"visual.blocks.25.mlp.gate_proj",
"visual.blocks.25.mlp.up_proj",
"visual.blocks.25.mlp.down_proj",
"visual.blocks.26.attn.qkv",
"visual.blocks.26.attn.proj",
"visual.blocks.26.mlp.gate_proj",
"visual.blocks.26.mlp.up_proj",
"visual.blocks.26.mlp.down_proj",
"visual.blocks.27.attn.qkv",
"visual.blocks.27.attn.proj",
"visual.blocks.27.mlp.gate_proj",
"visual.blocks.27.mlp.up_proj",
"visual.blocks.27.mlp.down_proj",
"visual.blocks.28.attn.qkv",
"visual.blocks.28.attn.proj",
"visual.blocks.28.mlp.gate_proj",
"visual.blocks.28.mlp.up_proj",
"visual.blocks.28.mlp.down_proj",
"visual.blocks.29.attn.qkv",
"visual.blocks.29.attn.proj",
"visual.blocks.29.mlp.gate_proj",
"visual.blocks.29.mlp.up_proj",
"visual.blocks.29.mlp.down_proj",
"visual.blocks.30.attn.qkv",
"visual.blocks.30.attn.proj",
"visual.blocks.30.mlp.gate_proj",
"visual.blocks.30.mlp.up_proj",
"visual.blocks.30.mlp.down_proj",
"visual.blocks.31.attn.qkv",
"visual.blocks.31.attn.proj",
"visual.blocks.31.mlp.gate_proj",
"visual.blocks.31.mlp.up_proj",
"visual.blocks.31.mlp.down_proj",
"visual.merger.mlp.0",
"visual.merger.mlp.2",
"lm_head"
],
"kv_cache_scheme": null,
"quant_method": "compressed-tensors",
"quantization_status": "compressed",
"sparsity_config": {
"format": "dense",
"global_sparsity": 0.12852197810556548,
"ignore": [
"visual.blocks.0.attn.qkv",
"visual.blocks.0.attn.proj",
"visual.blocks.0.mlp.gate_proj",
"visual.blocks.0.mlp.up_proj",
"visual.blocks.0.mlp.down_proj",
"visual.blocks.1.attn.qkv",
"visual.blocks.1.attn.proj",
"visual.blocks.1.mlp.gate_proj",
"visual.blocks.1.mlp.up_proj",
"visual.blocks.1.mlp.down_proj",
"visual.blocks.2.attn.qkv",
"visual.blocks.2.attn.proj",
"visual.blocks.2.mlp.gate_proj",
"visual.blocks.2.mlp.up_proj",
"visual.blocks.2.mlp.down_proj",
"visual.blocks.3.attn.qkv",
"visual.blocks.3.attn.proj",
"visual.blocks.3.mlp.gate_proj",
"visual.blocks.3.mlp.up_proj",
"visual.blocks.3.mlp.down_proj",
"visual.blocks.4.attn.qkv",
"visual.blocks.4.attn.proj",
"visual.blocks.4.mlp.gate_proj",
"visual.blocks.4.mlp.up_proj",
"visual.blocks.4.mlp.down_proj",
"visual.blocks.5.attn.qkv",
"visual.blocks.5.attn.proj",
"visual.blocks.5.mlp.gate_proj",
"visual.blocks.5.mlp.up_proj",
"visual.blocks.5.mlp.down_proj",
"visual.blocks.6.attn.qkv",
"visual.blocks.6.attn.proj",
"visual.blocks.6.mlp.gate_proj",
"visual.blocks.6.mlp.up_proj",
"visual.blocks.6.mlp.down_proj",
"visual.blocks.7.attn.qkv",
"visual.blocks.7.attn.proj",
"visual.blocks.7.mlp.gate_proj",
"visual.blocks.7.mlp.up_proj",
"visual.blocks.7.mlp.down_proj",
"visual.blocks.8.attn.qkv",
"visual.blocks.8.attn.proj",
"visual.blocks.8.mlp.gate_proj",
"visual.blocks.8.mlp.up_proj",
"visual.blocks.8.mlp.down_proj",
"visual.blocks.9.attn.qkv",
"visual.blocks.9.attn.proj",
"visual.blocks.9.mlp.gate_proj",
"visual.blocks.9.mlp.up_proj",
"visual.blocks.9.mlp.down_proj",
"visual.blocks.10.attn.qkv",
"visual.blocks.10.attn.proj",
"visual.blocks.10.mlp.gate_proj",
"visual.blocks.10.mlp.up_proj",
"visual.blocks.10.mlp.down_proj",
"visual.blocks.11.attn.qkv",
"visual.blocks.11.attn.proj",
"visual.blocks.11.mlp.gate_proj",
"visual.blocks.11.mlp.up_proj",
"visual.blocks.11.mlp.down_proj",
"visual.blocks.12.attn.qkv",
"visual.blocks.12.attn.proj",
"visual.blocks.12.mlp.gate_proj",
"visual.blocks.12.mlp.up_proj",
"visual.blocks.12.mlp.down_proj",
"visual.blocks.13.attn.qkv",
"visual.blocks.13.attn.proj",
"visual.blocks.13.mlp.gate_proj",
"visual.blocks.13.mlp.up_proj",
"visual.blocks.13.mlp.down_proj",
"visual.blocks.14.attn.qkv",
"visual.blocks.14.attn.proj",
"visual.blocks.14.mlp.gate_proj",
"visual.blocks.14.mlp.up_proj",
"visual.blocks.14.mlp.down_proj",
"visual.blocks.15.attn.qkv",
"visual.blocks.15.attn.proj",
"visual.blocks.15.mlp.gate_proj",
"visual.blocks.15.mlp.up_proj",
"visual.blocks.15.mlp.down_proj",
"visual.blocks.16.attn.qkv",
"visual.blocks.16.attn.proj",
"visual.blocks.16.mlp.gate_proj",
"visual.blocks.16.mlp.up_proj",
"visual.blocks.16.mlp.down_proj",
"visual.blocks.17.attn.qkv",
"visual.blocks.17.attn.proj",
"visual.blocks.17.mlp.gate_proj",
"visual.blocks.17.mlp.up_proj",
"visual.blocks.17.mlp.down_proj",
"visual.blocks.18.attn.qkv",
"visual.blocks.18.attn.proj",
"visual.blocks.18.mlp.gate_proj",
"visual.blocks.18.mlp.up_proj",
"visual.blocks.18.mlp.down_proj",
"visual.blocks.19.attn.qkv",
"visual.blocks.19.attn.proj",
"visual.blocks.19.mlp.gate_proj",
"visual.blocks.19.mlp.up_proj",
"visual.blocks.19.mlp.down_proj",
"visual.blocks.20.attn.qkv",
"visual.blocks.20.attn.proj",
"visual.blocks.20.mlp.gate_proj",
"visual.blocks.20.mlp.up_proj",
"visual.blocks.20.mlp.down_proj",
"visual.blocks.21.attn.qkv",
"visual.blocks.21.attn.proj",
"visual.blocks.21.mlp.gate_proj",
"visual.blocks.21.mlp.up_proj",
"visual.blocks.21.mlp.down_proj",
"visual.blocks.22.attn.qkv",
"visual.blocks.22.attn.proj",
"visual.blocks.22.mlp.gate_proj",
"visual.blocks.22.mlp.up_proj",
"visual.blocks.22.mlp.down_proj",
"visual.blocks.23.attn.qkv",
"visual.blocks.23.attn.proj",
"visual.blocks.23.mlp.gate_proj",
"visual.blocks.23.mlp.up_proj",
"visual.blocks.23.mlp.down_proj",
"visual.blocks.24.attn.qkv",
"visual.blocks.24.attn.proj",
"visual.blocks.24.mlp.gate_proj",
"visual.blocks.24.mlp.up_proj",
"visual.blocks.24.mlp.down_proj",
"visual.blocks.25.attn.qkv",
"visual.blocks.25.attn.proj",
"visual.blocks.25.mlp.gate_proj",
"visual.blocks.25.mlp.up_proj",
"visual.blocks.25.mlp.down_proj",
"visual.blocks.26.attn.qkv",
"visual.blocks.26.attn.proj",
"visual.blocks.26.mlp.gate_proj",
"visual.blocks.26.mlp.up_proj",
"visual.blocks.26.mlp.down_proj",
"visual.blocks.27.attn.qkv",
"visual.blocks.27.attn.proj",
"visual.blocks.27.mlp.gate_proj",
"visual.blocks.27.mlp.up_proj",
"visual.blocks.27.mlp.down_proj",
"visual.blocks.28.attn.qkv",
"visual.blocks.28.attn.proj",
"visual.blocks.28.mlp.gate_proj",
"visual.blocks.28.mlp.up_proj",
"visual.blocks.28.mlp.down_proj",
"visual.blocks.29.attn.qkv",
"visual.blocks.29.attn.proj",
"visual.blocks.29.mlp.gate_proj",
"visual.blocks.29.mlp.up_proj",
"visual.blocks.29.mlp.down_proj",
"visual.blocks.30.attn.qkv",
"visual.blocks.30.attn.proj",
"visual.blocks.30.mlp.gate_proj",
"visual.blocks.30.mlp.up_proj",
"visual.blocks.30.mlp.down_proj",
"visual.blocks.31.attn.qkv",
"visual.blocks.31.attn.proj",
"visual.blocks.31.mlp.gate_proj",
"visual.blocks.31.mlp.up_proj",
"visual.blocks.31.mlp.down_proj",
"visual.merger.mlp.0",
"visual.merger.mlp.2",
"model.layers.0.self_attn.q_proj",
"model.layers.0.self_attn.k_proj",
"model.layers.0.self_attn.v_proj",
"model.layers.0.self_attn.o_proj",
"model.layers.0.mlp.gate_proj",
"model.layers.0.mlp.up_proj",
"model.layers.0.mlp.down_proj",
"model.layers.1.self_attn.q_proj",
"model.layers.1.self_attn.k_proj",
"model.layers.1.self_attn.v_proj",
"model.layers.1.self_attn.o_proj",
"model.layers.1.mlp.gate_proj",
"model.layers.1.mlp.up_proj",
"model.layers.2.self_attn.q_proj",
"model.layers.2.self_attn.k_proj",
"model.layers.2.self_attn.v_proj",
"model.layers.2.self_attn.o_proj",
"model.layers.2.mlp.gate_proj",
"model.layers.2.mlp.up_proj",
"model.layers.3.self_attn.q_proj",
"model.layers.3.self_attn.k_proj",
"model.layers.3.self_attn.v_proj",
"model.layers.3.self_attn.o_proj",
"model.layers.3.mlp.gate_proj",
"model.layers.3.mlp.up_proj",
"model.layers.4.self_attn.q_proj",
"model.layers.4.self_attn.k_proj",
"model.layers.4.self_attn.v_proj",
"model.layers.4.self_attn.o_proj",
"model.layers.4.mlp.gate_proj",
"model.layers.4.mlp.up_proj",
"model.layers.4.mlp.down_proj",
"model.layers.5.self_attn.q_proj",
"model.layers.5.self_attn.k_proj",
"model.layers.5.self_attn.v_proj",
"model.layers.5.self_attn.o_proj",
"model.layers.5.mlp.gate_proj",
"model.layers.5.mlp.up_proj",
"model.layers.5.mlp.down_proj",
"model.layers.6.self_attn.q_proj",
"model.layers.6.self_attn.k_proj",
"model.layers.6.self_attn.v_proj",
"model.layers.6.self_attn.o_proj",
"model.layers.6.mlp.gate_proj",
"model.layers.6.mlp.up_proj",
"model.layers.6.mlp.down_proj",
"model.layers.7.self_attn.q_proj",
"model.layers.7.self_attn.k_proj",
"model.layers.7.self_attn.v_proj",
"model.layers.7.self_attn.o_proj",
"model.layers.7.mlp.gate_proj",
"model.layers.7.mlp.up_proj",
"model.layers.7.mlp.down_proj",
"model.layers.8.self_attn.q_proj",
"model.layers.8.self_attn.k_proj",
"model.layers.8.self_attn.v_proj",
"model.layers.8.self_attn.o_proj",
"model.layers.8.mlp.gate_proj",
"model.layers.8.mlp.up_proj",
"model.layers.8.mlp.down_proj",
"model.layers.9.self_attn.q_proj",
"model.layers.9.self_attn.k_proj",
"model.layers.9.self_attn.v_proj",
"model.layers.9.self_attn.o_proj",
"model.layers.9.mlp.gate_proj",
"model.layers.9.mlp.up_proj",
"model.layers.9.mlp.down_proj",
"model.layers.10.self_attn.q_proj",
"model.layers.10.self_attn.k_proj",
"model.layers.10.self_attn.v_proj",
"model.layers.10.self_attn.o_proj",
"model.layers.10.mlp.gate_proj",
"model.layers.10.mlp.up_proj",
"model.layers.10.mlp.down_proj",
"model.layers.11.self_attn.q_proj",
"model.layers.11.self_attn.k_proj",
"model.layers.11.self_attn.v_proj",
"model.layers.11.self_attn.o_proj",
"model.layers.11.mlp.gate_proj",
"model.layers.11.mlp.up_proj",
"model.layers.11.mlp.down_proj",
"model.layers.12.self_attn.q_proj",
"model.layers.12.self_attn.k_proj",
"model.layers.12.self_attn.v_proj",
"model.layers.12.self_attn.o_proj",
"model.layers.12.mlp.gate_proj",
"model.layers.12.mlp.up_proj",
"model.layers.12.mlp.down_proj",
"model.layers.13.self_attn.q_proj",
"model.layers.13.self_attn.k_proj",
"model.layers.13.self_attn.v_proj",
"model.layers.13.self_attn.o_proj",
"model.layers.13.mlp.gate_proj",
"model.layers.13.mlp.up_proj",
"model.layers.13.mlp.down_proj",
"model.layers.14.self_attn.q_proj",
"model.layers.14.self_attn.k_proj",
"model.layers.14.self_attn.v_proj",
"model.layers.14.self_attn.o_proj",
"model.layers.14.mlp.gate_proj",
"model.layers.14.mlp.up_proj",
"model.layers.14.mlp.down_proj",
"model.layers.15.self_attn.q_proj",
"model.layers.15.self_attn.k_proj",
"model.layers.15.self_attn.v_proj",
"model.layers.15.self_attn.o_proj",
"model.layers.15.mlp.gate_proj",
"model.layers.15.mlp.up_proj",
"model.layers.15.mlp.down_proj",
"model.layers.16.self_attn.q_proj",
"model.layers.16.self_attn.k_proj",
"model.layers.16.self_attn.v_proj",
"model.layers.16.self_attn.o_proj",
"model.layers.16.mlp.gate_proj",
"model.layers.16.mlp.up_proj",
"model.layers.16.mlp.down_proj",
"model.layers.17.self_attn.q_proj",
"model.layers.17.self_attn.k_proj",
"model.layers.17.self_attn.v_proj",
"model.layers.17.self_attn.o_proj",
"model.layers.17.mlp.gate_proj",
"model.layers.17.mlp.up_proj",
"model.layers.17.mlp.down_proj",
"model.layers.18.self_attn.q_proj",
"model.layers.18.self_attn.k_proj",
"model.layers.18.self_attn.v_proj",
"model.layers.18.self_attn.o_proj",
"model.layers.18.mlp.gate_proj",
"model.layers.18.mlp.up_proj",
"model.layers.18.mlp.down_proj",
"model.layers.19.self_attn.q_proj",
"model.layers.19.self_attn.k_proj",
"model.layers.19.self_attn.v_proj",
"model.layers.19.self_attn.o_proj",
"model.layers.19.mlp.gate_proj",
"model.layers.19.mlp.up_proj",
"model.layers.19.mlp.down_proj",
"model.layers.20.self_attn.q_proj",
"model.layers.20.self_attn.k_proj",
"model.layers.20.self_attn.v_proj",
"model.layers.20.self_attn.o_proj",
"model.layers.20.mlp.gate_proj",
"model.layers.20.mlp.up_proj",
"model.layers.20.mlp.down_proj",
"model.layers.21.self_attn.q_proj",
"model.layers.21.self_attn.k_proj",
"model.layers.21.self_attn.v_proj",
"model.layers.21.self_attn.o_proj",
"model.layers.21.mlp.gate_proj",
"model.layers.21.mlp.up_proj",
"model.layers.21.mlp.down_proj",
"model.layers.22.self_attn.q_proj",
"model.layers.22.self_attn.k_proj",
"model.layers.22.self_attn.v_proj",
"model.layers.22.self_attn.o_proj",
"model.layers.22.mlp.gate_proj",
"model.layers.22.mlp.up_proj",
"model.layers.22.mlp.down_proj",
"model.layers.23.self_attn.q_proj",
"model.layers.23.self_attn.k_proj",
"model.layers.23.self_attn.v_proj",
"model.layers.23.self_attn.o_proj",
"model.layers.23.mlp.gate_proj",
"model.layers.23.mlp.up_proj",
"model.layers.23.mlp.down_proj",
"model.layers.24.self_attn.q_proj",
"model.layers.24.self_attn.k_proj",
"model.layers.24.self_attn.v_proj",
"model.layers.24.self_attn.o_proj",
"model.layers.24.mlp.gate_proj",
"model.layers.24.mlp.up_proj",
"model.layers.24.mlp.down_proj",
"model.layers.25.self_attn.q_proj",
"model.layers.25.self_attn.k_proj",
"model.layers.25.self_attn.v_proj",
"model.layers.25.self_attn.o_proj",
"model.layers.25.mlp.gate_proj",
"model.layers.25.mlp.up_proj",
"model.layers.25.mlp.down_proj",
"model.layers.26.self_attn.q_proj",
"model.layers.26.self_attn.k_proj",
"model.layers.26.self_attn.v_proj",
"model.layers.26.self_attn.o_proj",
"model.layers.26.mlp.gate_proj",
"model.layers.26.mlp.up_proj",
"model.layers.26.mlp.down_proj",
"model.layers.27.self_attn.q_proj",
"model.layers.27.self_attn.k_proj",
"model.layers.27.self_attn.v_proj",
"model.layers.27.self_attn.o_proj",
"model.layers.27.mlp.gate_proj",
"model.layers.27.mlp.up_proj",
"model.layers.27.mlp.down_proj",
"model.layers.28.self_attn.q_proj",
"model.layers.28.self_attn.k_proj",
"model.layers.28.self_attn.v_proj",
"model.layers.28.self_attn.o_proj",
"model.layers.28.mlp.gate_proj",
"model.layers.28.mlp.up_proj",
"model.layers.28.mlp.down_proj",
"model.layers.29.self_attn.q_proj",
"model.layers.29.self_attn.k_proj",
"model.layers.29.self_attn.v_proj",
"model.layers.29.self_attn.o_proj",
"model.layers.29.mlp.gate_proj",
"model.layers.29.mlp.up_proj",
"model.layers.29.mlp.down_proj",
"model.layers.30.self_attn.q_proj",
"model.layers.30.self_attn.k_proj",
"model.layers.30.self_attn.v_proj",
"model.layers.30.self_attn.o_proj",
"model.layers.30.mlp.gate_proj",
"model.layers.30.mlp.up_proj",
"model.layers.30.mlp.down_proj",
"model.layers.31.self_attn.q_proj",
"model.layers.31.self_attn.k_proj",
"model.layers.31.self_attn.v_proj",
"model.layers.31.self_attn.o_proj",
"model.layers.31.mlp.gate_proj",
"model.layers.31.mlp.up_proj",
"model.layers.31.mlp.down_proj",
"model.layers.32.self_attn.q_proj",
"model.layers.32.self_attn.k_proj",
"model.layers.32.self_attn.v_proj",
"model.layers.32.self_attn.o_proj",
"model.layers.32.mlp.gate_proj",
"model.layers.32.mlp.up_proj",
"model.layers.32.mlp.down_proj",
"model.layers.33.self_attn.q_proj",
"model.layers.33.self_attn.k_proj",
"model.layers.33.self_attn.v_proj",
"model.layers.33.self_attn.o_proj",
"model.layers.33.mlp.gate_proj",
"model.layers.33.mlp.up_proj",
"model.layers.33.mlp.down_proj",
"model.layers.34.self_attn.q_proj",
"model.layers.34.self_attn.k_proj",
"model.layers.34.self_attn.v_proj",
"model.layers.34.self_attn.o_proj",
"model.layers.34.mlp.gate_proj",
"model.layers.34.mlp.up_proj",
"model.layers.34.mlp.down_proj",
"model.layers.35.self_attn.q_proj",
"model.layers.35.self_attn.k_proj",
"model.layers.35.self_attn.v_proj",
"model.layers.35.self_attn.o_proj",
"model.layers.35.mlp.gate_proj",
"model.layers.35.mlp.up_proj",
"model.layers.35.mlp.down_proj",
"lm_head"
],
"registry_requires_subclass": false,
"sparsity_structure": "unstructured",
"targets": [
"model.layers.1.mlp.down_proj",
"model.layers.2.mlp.down_proj",
"model.layers.3.mlp.down_proj"
]
}
},
"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": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"out_hidden_size": 2048,
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 151936
}