SimpleTool-VLM-FP8 / quantization_config.json
Cialtion's picture
Upload FP8 Qwen3-VL-4B SimpleTool checkpoint
c052f27 verified
Raw History Blame Contribute Delete
20 kB
{
"config_groups": {
"group_0": {
"format": "float-quantized",
"input_activations": {
"actorder": null,
"block_structure": null,
"dynamic": true,
"group_size": null,
"num_bits": 8,
"observer": null,
"observer_kwargs": {},
"scale_dtype": null,
"strategy": "token",
"symmetric": true,
"type": "float",
"zp_dtype": null
},
"output_activations": null,
"targets": [
"model.language_model.layers.0.mlp.down_proj",
"model.language_model.layers.0.mlp.gate_proj",
"model.language_model.layers.0.mlp.up_proj",
"model.language_model.layers.0.self_attn.k_proj",
"model.language_model.layers.0.self_attn.o_proj",
"model.language_model.layers.0.self_attn.q_proj",
"model.language_model.layers.0.self_attn.v_proj",
"model.language_model.layers.1.mlp.down_proj",
"model.language_model.layers.1.mlp.gate_proj",
"model.language_model.layers.1.mlp.up_proj",
"model.language_model.layers.1.self_attn.k_proj",
"model.language_model.layers.1.self_attn.o_proj",
"model.language_model.layers.1.self_attn.q_proj",
"model.language_model.layers.1.self_attn.v_proj",
"model.language_model.layers.10.mlp.down_proj",
"model.language_model.layers.10.mlp.gate_proj",
"model.language_model.layers.10.mlp.up_proj",
"model.language_model.layers.10.self_attn.k_proj",
"model.language_model.layers.10.self_attn.o_proj",
"model.language_model.layers.10.self_attn.q_proj",
"model.language_model.layers.10.self_attn.v_proj",
"model.language_model.layers.11.mlp.down_proj",
"model.language_model.layers.11.mlp.gate_proj",
"model.language_model.layers.11.mlp.up_proj",
"model.language_model.layers.11.self_attn.k_proj",
"model.language_model.layers.11.self_attn.o_proj",
"model.language_model.layers.11.self_attn.q_proj",
"model.language_model.layers.11.self_attn.v_proj",
"model.language_model.layers.12.mlp.down_proj",
"model.language_model.layers.12.mlp.gate_proj",
"model.language_model.layers.12.mlp.up_proj",
"model.language_model.layers.12.self_attn.k_proj",
"model.language_model.layers.12.self_attn.o_proj",
"model.language_model.layers.12.self_attn.q_proj",
"model.language_model.layers.12.self_attn.v_proj",
"model.language_model.layers.13.mlp.down_proj",
"model.language_model.layers.13.mlp.gate_proj",
"model.language_model.layers.13.mlp.up_proj",
"model.language_model.layers.13.self_attn.k_proj",
"model.language_model.layers.13.self_attn.o_proj",
"model.language_model.layers.13.self_attn.q_proj",
"model.language_model.layers.13.self_attn.v_proj",
"model.language_model.layers.14.mlp.down_proj",
"model.language_model.layers.14.mlp.gate_proj",
"model.language_model.layers.14.mlp.up_proj",
"model.language_model.layers.14.self_attn.k_proj",
"model.language_model.layers.14.self_attn.o_proj",
"model.language_model.layers.14.self_attn.q_proj",
"model.language_model.layers.14.self_attn.v_proj",
"model.language_model.layers.15.mlp.down_proj",
"model.language_model.layers.15.mlp.gate_proj",
"model.language_model.layers.15.mlp.up_proj",
"model.language_model.layers.15.self_attn.k_proj",
"model.language_model.layers.15.self_attn.o_proj",
"model.language_model.layers.15.self_attn.q_proj",
"model.language_model.layers.15.self_attn.v_proj",
"model.language_model.layers.16.mlp.down_proj",
"model.language_model.layers.16.mlp.gate_proj",
"model.language_model.layers.16.mlp.up_proj",
"model.language_model.layers.16.self_attn.k_proj",
"model.language_model.layers.16.self_attn.o_proj",
"model.language_model.layers.16.self_attn.q_proj",
"model.language_model.layers.16.self_attn.v_proj",
"model.language_model.layers.17.mlp.down_proj",
"model.language_model.layers.17.mlp.gate_proj",
"model.language_model.layers.17.mlp.up_proj",
"model.language_model.layers.17.self_attn.k_proj",
"model.language_model.layers.17.self_attn.o_proj",
"model.language_model.layers.17.self_attn.q_proj",
"model.language_model.layers.17.self_attn.v_proj",
"model.language_model.layers.18.mlp.down_proj",
"model.language_model.layers.18.mlp.gate_proj",
"model.language_model.layers.18.mlp.up_proj",
"model.language_model.layers.18.self_attn.k_proj",
"model.language_model.layers.18.self_attn.o_proj",
"model.language_model.layers.18.self_attn.q_proj",
"model.language_model.layers.18.self_attn.v_proj",
"model.language_model.layers.19.mlp.down_proj",
"model.language_model.layers.19.mlp.gate_proj",
"model.language_model.layers.19.mlp.up_proj",
"model.language_model.layers.19.self_attn.k_proj",
"model.language_model.layers.19.self_attn.o_proj",
"model.language_model.layers.19.self_attn.q_proj",
"model.language_model.layers.19.self_attn.v_proj",
"model.language_model.layers.2.mlp.down_proj",
"model.language_model.layers.2.mlp.gate_proj",
"model.language_model.layers.2.mlp.up_proj",
"model.language_model.layers.2.self_attn.k_proj",
"model.language_model.layers.2.self_attn.o_proj",
"model.language_model.layers.2.self_attn.q_proj",
"model.language_model.layers.2.self_attn.v_proj",
"model.language_model.layers.20.mlp.down_proj",
"model.language_model.layers.20.mlp.gate_proj",
"model.language_model.layers.20.mlp.up_proj",
"model.language_model.layers.20.self_attn.k_proj",
"model.language_model.layers.20.self_attn.o_proj",
"model.language_model.layers.20.self_attn.q_proj",
"model.language_model.layers.20.self_attn.v_proj",
"model.language_model.layers.21.mlp.down_proj",
"model.language_model.layers.21.mlp.gate_proj",
"model.language_model.layers.21.mlp.up_proj",
"model.language_model.layers.21.self_attn.k_proj",
"model.language_model.layers.21.self_attn.o_proj",
"model.language_model.layers.21.self_attn.q_proj",
"model.language_model.layers.21.self_attn.v_proj",
"model.language_model.layers.22.mlp.down_proj",
"model.language_model.layers.22.mlp.gate_proj",
"model.language_model.layers.22.mlp.up_proj",
"model.language_model.layers.22.self_attn.k_proj",
"model.language_model.layers.22.self_attn.o_proj",
"model.language_model.layers.22.self_attn.q_proj",
"model.language_model.layers.22.self_attn.v_proj",
"model.language_model.layers.23.mlp.down_proj",
"model.language_model.layers.23.mlp.gate_proj",
"model.language_model.layers.23.mlp.up_proj",
"model.language_model.layers.23.self_attn.k_proj",
"model.language_model.layers.23.self_attn.o_proj",
"model.language_model.layers.23.self_attn.q_proj",
"model.language_model.layers.23.self_attn.v_proj",
"model.language_model.layers.24.mlp.down_proj",
"model.language_model.layers.24.mlp.gate_proj",
"model.language_model.layers.24.mlp.up_proj",
"model.language_model.layers.24.self_attn.k_proj",
"model.language_model.layers.24.self_attn.o_proj",
"model.language_model.layers.24.self_attn.q_proj",
"model.language_model.layers.24.self_attn.v_proj",
"model.language_model.layers.25.mlp.down_proj",
"model.language_model.layers.25.mlp.gate_proj",
"model.language_model.layers.25.mlp.up_proj",
"model.language_model.layers.25.self_attn.k_proj",
"model.language_model.layers.25.self_attn.o_proj",
"model.language_model.layers.25.self_attn.q_proj",
"model.language_model.layers.25.self_attn.v_proj",
"model.language_model.layers.26.mlp.down_proj",
"model.language_model.layers.26.mlp.gate_proj",
"model.language_model.layers.26.mlp.up_proj",
"model.language_model.layers.26.self_attn.k_proj",
"model.language_model.layers.26.self_attn.o_proj",
"model.language_model.layers.26.self_attn.q_proj",
"model.language_model.layers.26.self_attn.v_proj",
"model.language_model.layers.27.mlp.down_proj",
"model.language_model.layers.27.mlp.gate_proj",
"model.language_model.layers.27.mlp.up_proj",
"model.language_model.layers.27.self_attn.k_proj",
"model.language_model.layers.27.self_attn.o_proj",
"model.language_model.layers.27.self_attn.q_proj",
"model.language_model.layers.27.self_attn.v_proj",
"model.language_model.layers.28.mlp.down_proj",
"model.language_model.layers.28.mlp.gate_proj",
"model.language_model.layers.28.mlp.up_proj",
"model.language_model.layers.28.self_attn.k_proj",
"model.language_model.layers.28.self_attn.o_proj",
"model.language_model.layers.28.self_attn.q_proj",
"model.language_model.layers.28.self_attn.v_proj",
"model.language_model.layers.29.mlp.down_proj",
"model.language_model.layers.29.mlp.gate_proj",
"model.language_model.layers.29.mlp.up_proj",
"model.language_model.layers.29.self_attn.k_proj",
"model.language_model.layers.29.self_attn.o_proj",
"model.language_model.layers.29.self_attn.q_proj",
"model.language_model.layers.29.self_attn.v_proj",
"model.language_model.layers.3.mlp.down_proj",
"model.language_model.layers.3.mlp.gate_proj",
"model.language_model.layers.3.mlp.up_proj",
"model.language_model.layers.3.self_attn.k_proj",
"model.language_model.layers.3.self_attn.o_proj",
"model.language_model.layers.3.self_attn.q_proj",
"model.language_model.layers.3.self_attn.v_proj",
"model.language_model.layers.30.mlp.down_proj",
"model.language_model.layers.30.mlp.gate_proj",
"model.language_model.layers.30.mlp.up_proj",
"model.language_model.layers.30.self_attn.k_proj",
"model.language_model.layers.30.self_attn.o_proj",
"model.language_model.layers.30.self_attn.q_proj",
"model.language_model.layers.30.self_attn.v_proj",
"model.language_model.layers.31.mlp.down_proj",
"model.language_model.layers.31.mlp.gate_proj",
"model.language_model.layers.31.mlp.up_proj",
"model.language_model.layers.31.self_attn.k_proj",
"model.language_model.layers.31.self_attn.o_proj",
"model.language_model.layers.31.self_attn.q_proj",
"model.language_model.layers.31.self_attn.v_proj",
"model.language_model.layers.32.mlp.down_proj",
"model.language_model.layers.32.mlp.gate_proj",
"model.language_model.layers.32.mlp.up_proj",
"model.language_model.layers.32.self_attn.k_proj",
"model.language_model.layers.32.self_attn.o_proj",
"model.language_model.layers.32.self_attn.q_proj",
"model.language_model.layers.32.self_attn.v_proj",
"model.language_model.layers.33.mlp.down_proj",
"model.language_model.layers.33.mlp.gate_proj",
"model.language_model.layers.33.mlp.up_proj",
"model.language_model.layers.33.self_attn.k_proj",
"model.language_model.layers.33.self_attn.o_proj",
"model.language_model.layers.33.self_attn.q_proj",
"model.language_model.layers.33.self_attn.v_proj",
"model.language_model.layers.34.mlp.down_proj",
"model.language_model.layers.34.mlp.gate_proj",
"model.language_model.layers.34.mlp.up_proj",
"model.language_model.layers.34.self_attn.k_proj",
"model.language_model.layers.34.self_attn.o_proj",
"model.language_model.layers.34.self_attn.q_proj",
"model.language_model.layers.34.self_attn.v_proj",
"model.language_model.layers.35.mlp.down_proj",
"model.language_model.layers.35.mlp.gate_proj",
"model.language_model.layers.35.mlp.up_proj",
"model.language_model.layers.35.self_attn.k_proj",
"model.language_model.layers.35.self_attn.o_proj",
"model.language_model.layers.35.self_attn.q_proj",
"model.language_model.layers.35.self_attn.v_proj",
"model.language_model.layers.4.mlp.down_proj",
"model.language_model.layers.4.mlp.gate_proj",
"model.language_model.layers.4.mlp.up_proj",
"model.language_model.layers.4.self_attn.k_proj",
"model.language_model.layers.4.self_attn.o_proj",
"model.language_model.layers.4.self_attn.q_proj",
"model.language_model.layers.4.self_attn.v_proj",
"model.language_model.layers.5.mlp.down_proj",
"model.language_model.layers.5.mlp.gate_proj",
"model.language_model.layers.5.mlp.up_proj",
"model.language_model.layers.5.self_attn.k_proj",
"model.language_model.layers.5.self_attn.o_proj",
"model.language_model.layers.5.self_attn.q_proj",
"model.language_model.layers.5.self_attn.v_proj",
"model.language_model.layers.6.mlp.down_proj",
"model.language_model.layers.6.mlp.gate_proj",
"model.language_model.layers.6.mlp.up_proj",
"model.language_model.layers.6.self_attn.k_proj",
"model.language_model.layers.6.self_attn.o_proj",
"model.language_model.layers.6.self_attn.q_proj",
"model.language_model.layers.6.self_attn.v_proj",
"model.language_model.layers.7.mlp.down_proj",
"model.language_model.layers.7.mlp.gate_proj",
"model.language_model.layers.7.mlp.up_proj",
"model.language_model.layers.7.self_attn.k_proj",
"model.language_model.layers.7.self_attn.o_proj",
"model.language_model.layers.7.self_attn.q_proj",
"model.language_model.layers.7.self_attn.v_proj",
"model.language_model.layers.8.mlp.down_proj",
"model.language_model.layers.8.mlp.gate_proj",
"model.language_model.layers.8.mlp.up_proj",
"model.language_model.layers.8.self_attn.k_proj",
"model.language_model.layers.8.self_attn.o_proj",
"model.language_model.layers.8.self_attn.q_proj",
"model.language_model.layers.8.self_attn.v_proj",
"model.language_model.layers.9.mlp.down_proj",
"model.language_model.layers.9.mlp.gate_proj",
"model.language_model.layers.9.mlp.up_proj",
"model.language_model.layers.9.self_attn.k_proj",
"model.language_model.layers.9.self_attn.o_proj",
"model.language_model.layers.9.self_attn.q_proj",
"model.language_model.layers.9.self_attn.v_proj"
],
"weights": {
"actorder": null,
"block_structure": null,
"dynamic": false,
"group_size": null,
"num_bits": 8,
"observer": "memoryless_minmax",
"observer_kwargs": {},
"scale_dtype": null,
"strategy": "channel",
"symmetric": true,
"type": "float",
"zp_dtype": null
}
}
},
"format": "float-quantized",
"global_compression_ratio": null,
"ignore": [
"model.visual.blocks.0.attn.qkv",
"model.visual.blocks.0.attn.proj",
"model.visual.blocks.0.mlp.linear_fc1",
"model.visual.blocks.0.mlp.linear_fc2",
"model.visual.blocks.1.attn.qkv",
"model.visual.blocks.1.attn.proj",
"model.visual.blocks.1.mlp.linear_fc1",
"model.visual.blocks.1.mlp.linear_fc2",
"model.visual.blocks.2.attn.qkv",
"model.visual.blocks.2.attn.proj",
"model.visual.blocks.2.mlp.linear_fc1",
"model.visual.blocks.2.mlp.linear_fc2",
"model.visual.blocks.3.attn.qkv",
"model.visual.blocks.3.attn.proj",
"model.visual.blocks.3.mlp.linear_fc1",
"model.visual.blocks.3.mlp.linear_fc2",
"model.visual.blocks.4.attn.qkv",
"model.visual.blocks.4.attn.proj",
"model.visual.blocks.4.mlp.linear_fc1",
"model.visual.blocks.4.mlp.linear_fc2",
"model.visual.blocks.5.attn.qkv",
"model.visual.blocks.5.attn.proj",
"model.visual.blocks.5.mlp.linear_fc1",
"model.visual.blocks.5.mlp.linear_fc2",
"model.visual.blocks.6.attn.qkv",
"model.visual.blocks.6.attn.proj",
"model.visual.blocks.6.mlp.linear_fc1",
"model.visual.blocks.6.mlp.linear_fc2",
"model.visual.blocks.7.attn.qkv",
"model.visual.blocks.7.attn.proj",
"model.visual.blocks.7.mlp.linear_fc1",
"model.visual.blocks.7.mlp.linear_fc2",
"model.visual.blocks.8.attn.qkv",
"model.visual.blocks.8.attn.proj",
"model.visual.blocks.8.mlp.linear_fc1",
"model.visual.blocks.8.mlp.linear_fc2",
"model.visual.blocks.9.attn.qkv",
"model.visual.blocks.9.attn.proj",
"model.visual.blocks.9.mlp.linear_fc1",
"model.visual.blocks.9.mlp.linear_fc2",
"model.visual.blocks.10.attn.qkv",
"model.visual.blocks.10.attn.proj",
"model.visual.blocks.10.mlp.linear_fc1",
"model.visual.blocks.10.mlp.linear_fc2",
"model.visual.blocks.11.attn.qkv",
"model.visual.blocks.11.attn.proj",
"model.visual.blocks.11.mlp.linear_fc1",
"model.visual.blocks.11.mlp.linear_fc2",
"model.visual.blocks.12.attn.qkv",
"model.visual.blocks.12.attn.proj",
"model.visual.blocks.12.mlp.linear_fc1",
"model.visual.blocks.12.mlp.linear_fc2",
"model.visual.blocks.13.attn.qkv",
"model.visual.blocks.13.attn.proj",
"model.visual.blocks.13.mlp.linear_fc1",
"model.visual.blocks.13.mlp.linear_fc2",
"model.visual.blocks.14.attn.qkv",
"model.visual.blocks.14.attn.proj",
"model.visual.blocks.14.mlp.linear_fc1",
"model.visual.blocks.14.mlp.linear_fc2",
"model.visual.blocks.15.attn.qkv",
"model.visual.blocks.15.attn.proj",
"model.visual.blocks.15.mlp.linear_fc1",
"model.visual.blocks.15.mlp.linear_fc2",
"model.visual.blocks.16.attn.qkv",
"model.visual.blocks.16.attn.proj",
"model.visual.blocks.16.mlp.linear_fc1",
"model.visual.blocks.16.mlp.linear_fc2",
"model.visual.blocks.17.attn.qkv",
"model.visual.blocks.17.attn.proj",
"model.visual.blocks.17.mlp.linear_fc1",
"model.visual.blocks.17.mlp.linear_fc2",
"model.visual.blocks.18.attn.qkv",
"model.visual.blocks.18.attn.proj",
"model.visual.blocks.18.mlp.linear_fc1",
"model.visual.blocks.18.mlp.linear_fc2",
"model.visual.blocks.19.attn.qkv",
"model.visual.blocks.19.attn.proj",
"model.visual.blocks.19.mlp.linear_fc1",
"model.visual.blocks.19.mlp.linear_fc2",
"model.visual.blocks.20.attn.qkv",
"model.visual.blocks.20.attn.proj",
"model.visual.blocks.20.mlp.linear_fc1",
"model.visual.blocks.20.mlp.linear_fc2",
"model.visual.blocks.21.attn.qkv",
"model.visual.blocks.21.attn.proj",
"model.visual.blocks.21.mlp.linear_fc1",
"model.visual.blocks.21.mlp.linear_fc2",
"model.visual.blocks.22.attn.qkv",
"model.visual.blocks.22.attn.proj",
"model.visual.blocks.22.mlp.linear_fc1",
"model.visual.blocks.22.mlp.linear_fc2",
"model.visual.blocks.23.attn.qkv",
"model.visual.blocks.23.attn.proj",
"model.visual.blocks.23.mlp.linear_fc1",
"model.visual.blocks.23.mlp.linear_fc2",
"model.visual.merger.linear_fc1",
"model.visual.merger.linear_fc2",
"model.visual.deepstack_merger_list.0.linear_fc1",
"model.visual.deepstack_merger_list.0.linear_fc2",
"model.visual.deepstack_merger_list.1.linear_fc1",
"model.visual.deepstack_merger_list.1.linear_fc2",
"model.visual.deepstack_merger_list.2.linear_fc1",
"model.visual.deepstack_merger_list.2.linear_fc2",
"lm_head"
],
"kv_cache_scheme": null,
"quant_method": "compressed-tensors",
"quantization_status": "compressed",
"sparsity_config": {},
"transform_config": {},
"version": "0.16.0"
}