{ "model": "Qwen/Qwen3.8-27B-FP8", "revision": "017b9c7af6b5689d5dd426a76e0bc077eb5ca20a", "versions": { "torch": "2.11.0+cu130", "transformers": "5.17.0", "tokenizers": "0.23.2", "kernels": "0.16.0", "flash-linear-attention": "0.5.2", "triton": "3.6.0" }, "gpu": "NVIDIA L40S", "dtype": "bfloat16", "quantization": { "quant_method": "fp8", "modules_to_not_convert": [ "model.visual.blocks.0.attn.proj", "model.visual.blocks.0.attn.qkv", "model.visual.blocks.0.mlp.linear_fc1", "model.visual.blocks.0.mlp.linear_fc2", "visual.blocks.0.attn.proj", "visual.blocks.0.attn.qkv_proj", "visual.blocks.0.mlp.linear_fc1", "visual.blocks.0.mlp.linear_fc2", "model.visual.blocks.1.attn.proj", "model.visual.blocks.1.attn.qkv", "model.visual.blocks.1.mlp.linear_fc1", "model.visual.blocks.1.mlp.linear_fc2", "visual.blocks.1.attn.proj", "visual.blocks.1.attn.qkv_proj", "visual.blocks.1.mlp.linear_fc1", "visual.blocks.1.mlp.linear_fc2", "model.visual.blocks.2.attn.proj", "model.visual.blocks.2.attn.qkv", "model.visual.blocks.2.mlp.linear_fc1", "model.visual.blocks.2.mlp.linear_fc2", "visual.blocks.2.attn.proj", "visual.blocks.2.attn.qkv_proj", "visual.blocks.2.mlp.linear_fc1", "visual.blocks.2.mlp.linear_fc2", "model.visual.blocks.3.attn.proj", "model.visual.blocks.3.attn.qkv", "model.visual.blocks.3.mlp.linear_fc1", "model.visual.blocks.3.mlp.linear_fc2", "visual.blocks.3.attn.proj", "visual.blocks.3.attn.qkv_proj", "visual.blocks.3.mlp.linear_fc1", "visual.blocks.3.mlp.linear_fc2", "model.visual.blocks.4.attn.proj", "model.visual.blocks.4.attn.qkv", "model.visual.blocks.4.mlp.linear_fc1", "model.visual.blocks.4.mlp.linear_fc2", "visual.blocks.4.attn.proj", "visual.blocks.4.attn.qkv_proj", "visual.blocks.4.mlp.linear_fc1", "visual.blocks.4.mlp.linear_fc2", "model.visual.blocks.5.attn.proj", "model.visual.blocks.5.attn.qkv", "model.visual.blocks.5.mlp.linear_fc1", "model.visual.blocks.5.mlp.linear_fc2", "visual.blocks.5.attn.proj", "visual.blocks.5.attn.qkv_proj", "visual.blocks.5.mlp.linear_fc1", "visual.blocks.5.mlp.linear_fc2", "model.visual.blocks.6.attn.proj", "model.visual.blocks.6.attn.qkv", "model.visual.blocks.6.mlp.linear_fc1", "model.visual.blocks.6.mlp.linear_fc2", "visual.blocks.6.attn.proj", "visual.blocks.6.attn.qkv_proj", "visual.blocks.6.mlp.linear_fc1", "visual.blocks.6.mlp.linear_fc2", "model.visual.blocks.7.attn.proj", "model.visual.blocks.7.attn.qkv", "model.visual.blocks.7.mlp.linear_fc1", "model.visual.blocks.7.mlp.linear_fc2", "visual.blocks.7.attn.proj", "visual.blocks.7.attn.qkv_proj", "visual.blocks.7.mlp.linear_fc1", "visual.blocks.7.mlp.linear_fc2", "model.visual.blocks.8.attn.proj", "model.visual.blocks.8.attn.qkv", "model.visual.blocks.8.mlp.linear_fc1", "model.visual.blocks.8.mlp.linear_fc2", "visual.blocks.8.attn.proj", "visual.blocks.8.attn.qkv_proj", "visual.blocks.8.mlp.linear_fc1", "visual.blocks.8.mlp.linear_fc2", "model.visual.blocks.9.attn.proj", "model.visual.blocks.9.attn.qkv", "model.visual.blocks.9.mlp.linear_fc1", "model.visual.blocks.9.mlp.linear_fc2", "visual.blocks.9.attn.proj", "visual.blocks.9.attn.qkv_proj", "visual.blocks.9.mlp.linear_fc1", "visual.blocks.9.mlp.linear_fc2", "model.visual.blocks.10.attn.proj", "model.visual.blocks.10.attn.qkv", "model.visual.blocks.10.mlp.linear_fc1", "model.visual.blocks.10.mlp.linear_fc2", "visual.blocks.10.attn.proj", "visual.blocks.10.attn.qkv_proj", "visual.blocks.10.mlp.linear_fc1", "visual.blocks.10.mlp.linear_fc2", "model.visual.blocks.11.attn.proj", "model.visual.blocks.11.attn.qkv", "model.visual.blocks.11.mlp.linear_fc1", "model.visual.blocks.11.mlp.linear_fc2", "visual.blocks.11.attn.proj", "visual.blocks.11.attn.qkv_proj", "visual.blocks.11.mlp.linear_fc1", "visual.blocks.11.mlp.linear_fc2", "model.visual.blocks.12.attn.proj", "model.visual.blocks.12.attn.qkv", "model.visual.blocks.12.mlp.linear_fc1", "model.visual.blocks.12.mlp.linear_fc2", "visual.blocks.12.attn.proj", "visual.blocks.12.attn.qkv_proj", "visual.blocks.12.mlp.linear_fc1", "visual.blocks.12.mlp.linear_fc2", "model.visual.blocks.13.attn.proj", "model.visual.blocks.13.attn.qkv", "model.visual.blocks.13.mlp.linear_fc1", "model.visual.blocks.13.mlp.linear_fc2", "visual.blocks.13.attn.proj", "visual.blocks.13.attn.qkv_proj", "visual.blocks.13.mlp.linear_fc1", "visual.blocks.13.mlp.linear_fc2", "model.visual.blocks.14.attn.proj", "model.visual.blocks.14.attn.qkv", "model.visual.blocks.14.mlp.linear_fc1", "model.visual.blocks.14.mlp.linear_fc2", "visual.blocks.14.attn.proj", "visual.blocks.14.attn.qkv_proj", "visual.blocks.14.mlp.linear_fc1", "visual.blocks.14.mlp.linear_fc2", "model.visual.blocks.15.attn.proj", "model.visual.blocks.15.attn.qkv", "model.visual.blocks.15.mlp.linear_fc1", "model.visual.blocks.15.mlp.linear_fc2", "visual.blocks.15.attn.proj", "visual.blocks.15.attn.qkv_proj", "visual.blocks.15.mlp.linear_fc1", "visual.blocks.15.mlp.linear_fc2", "model.visual.blocks.16.attn.proj", "model.visual.blocks.16.attn.qkv", "model.visual.blocks.16.mlp.linear_fc1", "model.visual.blocks.16.mlp.linear_fc2", "visual.blocks.16.attn.proj", "visual.blocks.16.attn.qkv_proj", "visual.blocks.16.mlp.linear_fc1", "visual.blocks.16.mlp.linear_fc2", "model.visual.blocks.17.attn.proj", "model.visual.blocks.17.attn.qkv", "model.visual.blocks.17.mlp.linear_fc1", "model.visual.blocks.17.mlp.linear_fc2", "visual.blocks.17.attn.proj", "visual.blocks.17.attn.qkv_proj", "visual.blocks.17.mlp.linear_fc1", "visual.blocks.17.mlp.linear_fc2", "model.visual.blocks.18.attn.proj", "model.visual.blocks.18.attn.qkv", "model.visual.blocks.18.mlp.linear_fc1", "model.visual.blocks.18.mlp.linear_fc2", "visual.blocks.18.attn.proj", "visual.blocks.18.attn.qkv_proj", "visual.blocks.18.mlp.linear_fc1", "visual.blocks.18.mlp.linear_fc2", "model.visual.blocks.19.attn.proj", "model.visual.blocks.19.attn.qkv", "model.visual.blocks.19.mlp.linear_fc1", "model.visual.blocks.19.mlp.linear_fc2", "visual.blocks.19.attn.proj", "visual.blocks.19.attn.qkv_proj", "visual.blocks.19.mlp.linear_fc1", "visual.blocks.19.mlp.linear_fc2", "model.visual.blocks.20.attn.proj", "model.visual.blocks.20.attn.qkv", "model.visual.blocks.20.mlp.linear_fc1", "model.visual.blocks.20.mlp.linear_fc2", "visual.blocks.20.attn.proj", "visual.blocks.20.attn.qkv_proj", "visual.blocks.20.mlp.linear_fc1", "visual.blocks.20.mlp.linear_fc2", "model.visual.blocks.21.attn.proj", "model.visual.blocks.21.attn.qkv", "model.visual.blocks.21.mlp.linear_fc1", "model.visual.blocks.21.mlp.linear_fc2", "visual.blocks.21.attn.proj", "visual.blocks.21.attn.qkv_proj", "visual.blocks.21.mlp.linear_fc1", "visual.blocks.21.mlp.linear_fc2", "model.visual.blocks.22.attn.proj", "model.visual.blocks.22.attn.qkv", "model.visual.blocks.22.mlp.linear_fc1", "model.visual.blocks.22.mlp.linear_fc2", "visual.blocks.22.attn.proj", "visual.blocks.22.attn.qkv_proj", "visual.blocks.22.mlp.linear_fc1", "visual.blocks.22.mlp.linear_fc2", "model.visual.blocks.23.attn.proj", "model.visual.blocks.23.attn.qkv", "model.visual.blocks.23.mlp.linear_fc1", "model.visual.blocks.23.mlp.linear_fc2", "visual.blocks.23.attn.proj", "visual.blocks.23.attn.qkv_proj", "visual.blocks.23.mlp.linear_fc1", "visual.blocks.23.mlp.linear_fc2", "model.visual.blocks.24.attn.proj", "model.visual.blocks.24.attn.qkv", "model.visual.blocks.24.mlp.linear_fc1", "model.visual.blocks.24.mlp.linear_fc2", "visual.blocks.24.attn.proj", "visual.blocks.24.attn.qkv_proj", "visual.blocks.24.mlp.linear_fc1", "visual.blocks.24.mlp.linear_fc2", "model.visual.blocks.25.attn.proj", "model.visual.blocks.25.attn.qkv", "model.visual.blocks.25.mlp.linear_fc1", "model.visual.blocks.25.mlp.linear_fc2", "visual.blocks.25.attn.proj", "visual.blocks.25.attn.qkv_proj", "visual.blocks.25.mlp.linear_fc1", "visual.blocks.25.mlp.linear_fc2", "model.visual.blocks.26.attn.proj", "model.visual.blocks.26.attn.qkv", "model.visual.blocks.26.mlp.linear_fc1", "model.visual.blocks.26.mlp.linear_fc2", "visual.blocks.26.attn.proj", "visual.blocks.26.attn.qkv_proj", "visual.blocks.26.mlp.linear_fc1", "visual.blocks.26.mlp.linear_fc2", "model.visual.deepstack_merger_list.0.linear_fc1", "model.visual.deepstack_merger_list.0.linear_fc2", "model.visual.deepstack_merger_list.0.norm", "visual.deepstack_merger_list.0.linear_fc1", "visual.deepstack_merger_list.0.linear_fc2", "visual.deepstack_merger_list.0.norm", "model.visual.deepstack_merger_list.1.linear_fc1", "model.visual.deepstack_merger_list.1.linear_fc2", "model.visual.deepstack_merger_list.1.norm", "visual.deepstack_merger_list.1.linear_fc1", "visual.deepstack_merger_list.1.linear_fc2", "visual.deepstack_merger_list.1.norm", "model.visual.deepstack_merger_list.2.linear_fc1", "model.visual.deepstack_merger_list.2.linear_fc2", "model.visual.deepstack_merger_list.2.norm", "visual.deepstack_merger_list.2.linear_fc1", "visual.deepstack_merger_list.2.linear_fc2", "visual.deepstack_merger_list.2.norm", "model.visual.merger.linear_fc1", "model.visual.merger.linear_fc2", "model.visual.merger.norm", "model.visual.patch_embed.proj", "model.visual.pos_embed", "visual.merger.linear_fc1", "visual.merger.linear_fc2", "visual.merger.norm", "visual.patch_embed.proj", "visual.pos_embed", "visual", "model.visual", "lm_head", "model.embed_tokens", "model.language_model.layers.0.input_layernorm", "model.language_model.layers.0.mlp.shared_expert_gate", "model.language_model.layers.0.post_attention_layernorm", "model.language_model.layers.0.linear_attn.A_log", "model.language_model.layers.0.linear_attn.conv1d", "model.language_model.layers.0.linear_attn.dt_bias", "model.language_model.layers.0.linear_attn.in_proj_ba", "model.language_model.layers.0.linear_attn.in_proj_b", "model.language_model.layers.0.linear_attn.in_proj_a", "model.language_model.layers.0.linear_attn.norm", "model.language_model.layers.1.input_layernorm", "model.language_model.layers.1.mlp.shared_expert_gate", "model.language_model.layers.1.post_attention_layernorm", "model.language_model.layers.1.linear_attn.A_log", "model.language_model.layers.1.linear_attn.conv1d", "model.language_model.layers.1.linear_attn.dt_bias", "model.language_model.layers.1.linear_attn.in_proj_ba", "model.language_model.layers.1.linear_attn.in_proj_b", "model.language_model.layers.1.linear_attn.in_proj_a", "model.language_model.layers.1.linear_attn.norm", "model.language_model.layers.2.input_layernorm", "model.language_model.layers.2.mlp.shared_expert_gate", "model.language_model.layers.2.post_attention_layernorm", "model.language_model.layers.2.linear_attn.A_log", "model.language_model.layers.2.linear_attn.conv1d", "model.language_model.layers.2.linear_attn.dt_bias", "model.language_model.layers.2.linear_attn.in_proj_ba", "model.language_model.layers.2.linear_attn.in_proj_b", "model.language_model.layers.2.linear_attn.in_proj_a", "model.language_model.layers.2.linear_attn.norm", "model.language_model.layers.3.input_layernorm", "model.language_model.layers.3.mlp.shared_expert_gate", "model.language_model.layers.3.post_attention_layernorm", "model.language_model.layers.3.self_attn.k_norm", "model.language_model.layers.3.self_attn.q_norm", "model.language_model.layers.4.input_layernorm", "model.language_model.layers.4.mlp.shared_expert_gate", "model.language_model.layers.4.post_attention_layernorm", "model.language_model.layers.4.linear_attn.A_log", "model.language_model.layers.4.linear_attn.conv1d", "model.language_model.layers.4.linear_attn.dt_bias", "model.language_model.layers.4.linear_attn.in_proj_ba", "model.language_model.layers.4.linear_attn.in_proj_b", "model.language_model.layers.4.linear_attn.in_proj_a", "model.language_model.layers.4.linear_attn.norm", "model.language_model.layers.5.input_layernorm", "model.language_model.layers.5.mlp.shared_expert_gate", "model.language_model.layers.5.post_attention_layernorm", "model.language_model.layers.5.linear_attn.A_log", "model.language_model.layers.5.linear_attn.conv1d", "model.language_model.layers.5.linear_attn.dt_bias", "model.language_model.layers.5.linear_attn.in_proj_ba", "model.language_model.layers.5.linear_attn.in_proj_b", "model.language_model.layers.5.linear_attn.in_proj_a", "model.language_model.layers.5.linear_attn.norm", "model.language_model.layers.6.input_layernorm", "model.language_model.layers.6.mlp.shared_expert_gate", "model.language_model.layers.6.post_attention_layernorm", "model.language_model.layers.6.linear_attn.A_log", "model.language_model.layers.6.linear_attn.conv1d", "model.language_model.layers.6.linear_attn.dt_bias", "model.language_model.layers.6.linear_attn.in_proj_ba", "model.language_model.layers.6.linear_attn.in_proj_b", "model.language_model.layers.6.linear_attn.in_proj_a", "model.language_model.layers.6.linear_attn.norm", "model.language_model.layers.7.input_layernorm", "model.language_model.layers.7.mlp.shared_expert_gate", "model.language_model.layers.7.post_attention_layernorm", "model.language_model.layers.7.self_attn.k_norm", "model.language_model.layers.7.self_attn.q_norm", "model.language_model.layers.8.input_layernorm", "model.language_model.layers.8.mlp.shared_expert_gate", "model.language_model.layers.8.post_attention_layernorm", "model.language_model.layers.8.linear_attn.A_log", "model.language_model.layers.8.linear_attn.conv1d", "model.language_model.layers.8.linear_attn.dt_bias", "model.language_model.layers.8.linear_attn.in_proj_ba", "model.language_model.layers.8.linear_attn.in_proj_b", "model.language_model.layers.8.linear_attn.in_proj_a", "model.language_model.layers.8.linear_attn.norm", "model.language_model.layers.9.input_layernorm", "model.language_model.layers.9.mlp.shared_expert_gate", "model.language_model.layers.9.post_attention_layernorm", "model.language_model.layers.9.linear_attn.A_log", "model.language_model.layers.9.linear_attn.conv1d", "model.language_model.layers.9.linear_attn.dt_bias", "model.language_model.layers.9.linear_attn.in_proj_ba", "model.language_model.layers.9.linear_attn.in_proj_b", "model.language_model.layers.9.linear_attn.in_proj_a", "model.language_model.layers.9.linear_attn.norm", "model.language_model.layers.10.input_layernorm", "model.language_model.layers.10.mlp.shared_expert_gate", "model.language_model.layers.10.post_attention_layernorm", "model.language_model.layers.10.linear_attn.A_log", "model.language_model.layers.10.linear_attn.conv1d", "model.language_model.layers.10.linear_attn.dt_bias", "model.language_model.layers.10.linear_attn.in_proj_ba", "model.language_model.layers.10.linear_attn.in_proj_b", "model.language_model.layers.10.linear_attn.in_proj_a", "model.language_model.layers.10.linear_attn.norm", "model.language_model.layers.11.input_layernorm", "model.language_model.layers.11.mlp.shared_expert_gate", "model.language_model.layers.11.post_attention_layernorm", "model.language_model.layers.11.self_attn.k_norm", "model.language_model.layers.11.self_attn.q_norm", "model.language_model.layers.12.input_layernorm", "model.language_model.layers.12.mlp.shared_expert_gate", "model.language_model.layers.12.post_attention_layernorm", "model.language_model.layers.12.linear_attn.A_log", "model.language_model.layers.12.linear_attn.conv1d", "model.language_model.layers.12.linear_attn.dt_bias", "model.language_model.layers.12.linear_attn.in_proj_ba", "model.language_model.layers.12.linear_attn.in_proj_b", "model.language_model.layers.12.linear_attn.in_proj_a", "model.language_model.layers.12.linear_attn.norm", "model.language_model.layers.13.input_layernorm", "model.language_model.layers.13.mlp.shared_expert_gate", "model.language_model.layers.13.post_attention_layernorm", "model.language_model.layers.13.linear_attn.A_log", "model.language_model.layers.13.linear_attn.conv1d", "model.language_model.layers.13.linear_attn.dt_bias", "model.language_model.layers.13.linear_attn.in_proj_ba", "model.language_model.layers.13.linear_attn.in_proj_b", "model.language_model.layers.13.linear_attn.in_proj_a", "model.language_model.layers.13.linear_attn.norm", "model.language_model.layers.14.input_layernorm", "model.language_model.layers.14.mlp.shared_expert_gate", "model.language_model.layers.14.post_attention_layernorm", "model.language_model.layers.14.linear_attn.A_log", "model.language_model.layers.14.linear_attn.conv1d", "model.language_model.layers.14.linear_attn.dt_bias", "model.language_model.layers.14.linear_attn.in_proj_ba", "model.language_model.layers.14.linear_attn.in_proj_b", "model.language_model.layers.14.linear_attn.in_proj_a", "model.language_model.layers.14.linear_attn.norm", "model.language_model.layers.15.input_layernorm", "model.language_model.layers.15.mlp.shared_expert_gate", "model.language_model.layers.15.post_attention_layernorm", "model.language_model.layers.15.self_attn.k_norm", "model.language_model.layers.15.self_attn.q_norm", "model.language_model.layers.16.input_layernorm", "model.language_model.layers.16.mlp.shared_expert_gate", "model.language_model.layers.16.post_attention_layernorm", "model.language_model.layers.16.linear_attn.A_log", "model.language_model.layers.16.linear_attn.conv1d", "model.language_model.layers.16.linear_attn.dt_bias", "model.language_model.layers.16.linear_attn.in_proj_ba", "model.language_model.layers.16.linear_attn.in_proj_b", "model.language_model.layers.16.linear_attn.in_proj_a", "model.language_model.layers.16.linear_attn.norm", "model.language_model.layers.17.input_layernorm", "model.language_model.layers.17.mlp.shared_expert_gate", "model.language_model.layers.17.post_attention_layernorm", "model.language_model.layers.17.linear_attn.A_log", "model.language_model.layers.17.linear_attn.conv1d", "model.language_model.layers.17.linear_attn.dt_bias", "model.language_model.layers.17.linear_attn.in_proj_ba", "model.language_model.layers.17.linear_attn.in_proj_b", "model.language_model.layers.17.linear_attn.in_proj_a", "model.language_model.layers.17.linear_attn.norm", "model.language_model.layers.18.input_layernorm", "model.language_model.layers.18.mlp.shared_expert_gate", "model.language_model.layers.18.post_attention_layernorm", "model.language_model.layers.18.linear_attn.A_log", "model.language_model.layers.18.linear_attn.conv1d", "model.language_model.layers.18.linear_attn.dt_bias", "model.language_model.layers.18.linear_attn.in_proj_ba", "model.language_model.layers.18.linear_attn.in_proj_b", "model.language_model.layers.18.linear_attn.in_proj_a", "model.language_model.layers.18.linear_attn.norm", "model.language_model.layers.19.input_layernorm", "model.language_model.layers.19.mlp.shared_expert_gate", "model.language_model.layers.19.post_attention_layernorm", "model.language_model.layers.19.self_attn.k_norm", "model.language_model.layers.19.self_attn.q_norm", "model.language_model.layers.20.input_layernorm", "model.language_model.layers.20.mlp.shared_expert_gate", "model.language_model.layers.20.post_attention_layernorm", "model.language_model.layers.20.linear_attn.A_log", "model.language_model.layers.20.linear_attn.conv1d", "model.language_model.layers.20.linear_attn.dt_bias", "model.language_model.layers.20.linear_attn.in_proj_ba", "model.language_model.layers.20.linear_attn.in_proj_b", "model.language_model.layers.20.linear_attn.in_proj_a", "model.language_model.layers.20.linear_attn.norm", "model.language_model.layers.21.input_layernorm", "model.language_model.layers.21.mlp.shared_expert_gate", "model.language_model.layers.21.post_attention_layernorm", "model.language_model.layers.21.linear_attn.A_log", "model.language_model.layers.21.linear_attn.conv1d", "model.language_model.layers.21.linear_attn.dt_bias", "model.language_model.layers.21.linear_attn.in_proj_ba", "model.language_model.layers.21.linear_attn.in_proj_b", "model.language_model.layers.21.linear_attn.in_proj_a", "model.language_model.layers.21.linear_attn.norm", "model.language_model.layers.22.input_layernorm", "model.language_model.layers.22.mlp.shared_expert_gate", "model.language_model.layers.22.post_attention_layernorm", "model.language_model.layers.22.linear_attn.A_log", "model.language_model.layers.22.linear_attn.conv1d", "model.language_model.layers.22.linear_attn.dt_bias", "model.language_model.layers.22.linear_attn.in_proj_ba", "model.language_model.layers.22.linear_attn.in_proj_b", "model.language_model.layers.22.linear_attn.in_proj_a", "model.language_model.layers.22.linear_attn.norm", "model.language_model.layers.23.input_layernorm", "model.language_model.layers.23.mlp.shared_expert_gate", "model.language_model.layers.23.post_attention_layernorm", "model.language_model.layers.23.self_attn.k_norm", "model.language_model.layers.23.self_attn.q_norm", "model.language_model.layers.24.input_layernorm", "model.language_model.layers.24.mlp.shared_expert_gate", "model.language_model.layers.24.post_attention_layernorm", "model.language_model.layers.24.linear_attn.A_log", "model.language_model.layers.24.linear_attn.conv1d", "model.language_model.layers.24.linear_attn.dt_bias", "model.language_model.layers.24.linear_attn.in_proj_ba", "model.language_model.layers.24.linear_attn.in_proj_b", "model.language_model.layers.24.linear_attn.in_proj_a", "model.language_model.layers.24.linear_attn.norm", "model.language_model.layers.25.input_layernorm", "model.language_model.layers.25.mlp.shared_expert_gate", "model.language_model.layers.25.post_attention_layernorm", "model.language_model.layers.25.linear_attn.A_log", "model.language_model.layers.25.linear_attn.conv1d", "model.language_model.layers.25.linear_attn.dt_bias", "model.language_model.layers.25.linear_attn.in_proj_ba", "model.language_model.layers.25.linear_attn.in_proj_b", "model.language_model.layers.25.linear_attn.in_proj_a", "model.language_model.layers.25.linear_attn.norm", "model.language_model.layers.26.input_layernorm", "model.language_model.layers.26.mlp.shared_expert_gate", "model.language_model.layers.26.post_attention_layernorm", "model.language_model.layers.26.linear_attn.A_log", "model.language_model.layers.26.linear_attn.conv1d", "model.language_model.layers.26.linear_attn.dt_bias", "model.language_model.layers.26.linear_attn.in_proj_ba", "model.language_model.layers.26.linear_attn.in_proj_b", "model.language_model.layers.26.linear_attn.in_proj_a", "model.language_model.layers.26.linear_attn.norm", "model.language_model.layers.27.input_layernorm", "model.language_model.layers.27.mlp.shared_expert_gate", "model.language_model.layers.27.post_attention_layernorm", "model.language_model.layers.27.self_attn.k_norm", "model.language_model.layers.27.self_attn.q_norm", "model.language_model.layers.28.input_layernorm", "model.language_model.layers.28.mlp.shared_expert_gate", "model.language_model.layers.28.post_attention_layernorm", "model.language_model.layers.28.linear_attn.A_log", "model.language_model.layers.28.linear_attn.conv1d", "model.language_model.layers.28.linear_attn.dt_bias", "model.language_model.layers.28.linear_attn.in_proj_ba", "model.language_model.layers.28.linear_attn.in_proj_b", "model.language_model.layers.28.linear_attn.in_proj_a", "model.language_model.layers.28.linear_attn.norm", "model.language_model.layers.29.input_layernorm", "model.language_model.layers.29.mlp.shared_expert_gate", "model.language_model.layers.29.post_attention_layernorm", "model.language_model.layers.29.linear_attn.A_log", "model.language_model.layers.29.linear_attn.conv1d", "model.language_model.layers.29.linear_attn.dt_bias", "model.language_model.layers.29.linear_attn.in_proj_ba", "model.language_model.layers.29.linear_attn.in_proj_b", "model.language_model.layers.29.linear_attn.in_proj_a", "model.language_model.layers.29.linear_attn.norm", "model.language_model.layers.30.input_layernorm", "model.language_model.layers.30.mlp.shared_expert_gate", "model.language_model.layers.30.post_attention_layernorm", "model.language_model.layers.30.linear_attn.A_log", "model.language_model.layers.30.linear_attn.conv1d", "model.language_model.layers.30.linear_attn.dt_bias", "model.language_model.layers.30.linear_attn.in_proj_ba", "model.language_model.layers.30.linear_attn.in_proj_b", "model.language_model.layers.30.linear_attn.in_proj_a", "model.language_model.layers.30.linear_attn.norm", "model.language_model.layers.31.input_layernorm", "model.language_model.layers.31.mlp.shared_expert_gate", "model.language_model.layers.31.post_attention_layernorm", "model.language_model.layers.31.self_attn.k_norm", "model.language_model.layers.31.self_attn.q_norm", "model.language_model.layers.32.input_layernorm", "model.language_model.layers.32.mlp.shared_expert_gate", "model.language_model.layers.32.post_attention_layernorm", "model.language_model.layers.32.linear_attn.A_log", "model.language_model.layers.32.linear_attn.conv1d", "model.language_model.layers.32.linear_attn.dt_bias", "model.language_model.layers.32.linear_attn.in_proj_ba", "model.language_model.layers.32.linear_attn.in_proj_b", "model.language_model.layers.32.linear_attn.in_proj_a", "model.language_model.layers.32.linear_attn.norm", "model.language_model.layers.33.input_layernorm", "model.language_model.layers.33.mlp.shared_expert_gate", "model.language_model.layers.33.post_attention_layernorm", "model.language_model.layers.33.linear_attn.A_log", "model.language_model.layers.33.linear_attn.conv1d", "model.language_model.layers.33.linear_attn.dt_bias", "model.language_model.layers.33.linear_attn.in_proj_ba", "model.language_model.layers.33.linear_attn.in_proj_b", "model.language_model.layers.33.linear_attn.in_proj_a", "model.language_model.layers.33.linear_attn.norm", "model.language_model.layers.34.input_layernorm", "model.language_model.layers.34.mlp.shared_expert_gate", "model.language_model.layers.34.post_attention_layernorm", "model.language_model.layers.34.linear_attn.A_log", "model.language_model.layers.34.linear_attn.conv1d", "model.language_model.layers.34.linear_attn.dt_bias", "model.language_model.layers.34.linear_attn.in_proj_ba", "model.language_model.layers.34.linear_attn.in_proj_b", "model.language_model.layers.34.linear_attn.in_proj_a", "model.language_model.layers.34.linear_attn.norm", "model.language_model.layers.35.input_layernorm", "model.language_model.layers.35.mlp.shared_expert_gate", "model.language_model.layers.35.post_attention_layernorm", "model.language_model.layers.35.self_attn.k_norm", "model.language_model.layers.35.self_attn.q_norm", "model.language_model.layers.36.input_layernorm", "model.language_model.layers.36.mlp.shared_expert_gate", "model.language_model.layers.36.post_attention_layernorm", "model.language_model.layers.36.linear_attn.A_log", "model.language_model.layers.36.linear_attn.conv1d", "model.language_model.layers.36.linear_attn.dt_bias", "model.language_model.layers.36.linear_attn.in_proj_ba", "model.language_model.layers.36.linear_attn.in_proj_b", "model.language_model.layers.36.linear_attn.in_proj_a", "model.language_model.layers.36.linear_attn.norm", "model.language_model.layers.37.input_layernorm", "model.language_model.layers.37.mlp.shared_expert_gate", "model.language_model.layers.37.post_attention_layernorm", "model.language_model.layers.37.linear_attn.A_log", "model.language_model.layers.37.linear_attn.conv1d", "model.language_model.layers.37.linear_attn.dt_bias", "model.language_model.layers.37.linear_attn.in_proj_ba", "model.language_model.layers.37.linear_attn.in_proj_b", "model.language_model.layers.37.linear_attn.in_proj_a", "model.language_model.layers.37.linear_attn.norm", "model.language_model.layers.38.input_layernorm", "model.language_model.layers.38.mlp.shared_expert_gate", "model.language_model.layers.38.post_attention_layernorm", "model.language_model.layers.38.linear_attn.A_log", "model.language_model.layers.38.linear_attn.conv1d", "model.language_model.layers.38.linear_attn.dt_bias", "model.language_model.layers.38.linear_attn.in_proj_ba", "model.language_model.layers.38.linear_attn.in_proj_b", "model.language_model.layers.38.linear_attn.in_proj_a", "model.language_model.layers.38.linear_attn.norm", "model.language_model.layers.39.input_layernorm", "model.language_model.layers.39.mlp.shared_expert_gate", "model.language_model.layers.39.post_attention_layernorm", "model.language_model.layers.39.self_attn.k_norm", "model.language_model.layers.39.self_attn.q_norm", "model.language_model.layers.40.input_layernorm", "model.language_model.layers.40.mlp.shared_expert_gate", "model.language_model.layers.40.post_attention_layernorm", "model.language_model.layers.40.linear_attn.A_log", "model.language_model.layers.40.linear_attn.conv1d", "model.language_model.layers.40.linear_attn.dt_bias", "model.language_model.layers.40.linear_attn.in_proj_ba", "model.language_model.layers.40.linear_attn.in_proj_b", "model.language_model.layers.40.linear_attn.in_proj_a", "model.language_model.layers.40.linear_attn.norm", "model.language_model.layers.41.input_layernorm", "model.language_model.layers.41.mlp.shared_expert_gate", "model.language_model.layers.41.post_attention_layernorm", "model.language_model.layers.41.linear_attn.A_log", "model.language_model.layers.41.linear_attn.conv1d", "model.language_model.layers.41.linear_attn.dt_bias", "model.language_model.layers.41.linear_attn.in_proj_ba", "model.language_model.layers.41.linear_attn.in_proj_b", "model.language_model.layers.41.linear_attn.in_proj_a", "model.language_model.layers.41.linear_attn.norm", "model.language_model.layers.42.input_layernorm", "model.language_model.layers.42.mlp.shared_expert_gate", "model.language_model.layers.42.post_attention_layernorm", "model.language_model.layers.42.linear_attn.A_log", "model.language_model.layers.42.linear_attn.conv1d", "model.language_model.layers.42.linear_attn.dt_bias", "model.language_model.layers.42.linear_attn.in_proj_ba", "model.language_model.layers.42.linear_attn.in_proj_b", "model.language_model.layers.42.linear_attn.in_proj_a", "model.language_model.layers.42.linear_attn.norm", "model.language_model.layers.43.input_layernorm", "model.language_model.layers.43.mlp.shared_expert_gate", "model.language_model.layers.43.post_attention_layernorm", "model.language_model.layers.43.self_attn.k_norm", "model.language_model.layers.43.self_attn.q_norm", "model.language_model.layers.44.input_layernorm", "model.language_model.layers.44.mlp.shared_expert_gate", "model.language_model.layers.44.post_attention_layernorm", "model.language_model.layers.44.linear_attn.A_log", "model.language_model.layers.44.linear_attn.conv1d", "model.language_model.layers.44.linear_attn.dt_bias", "model.language_model.layers.44.linear_attn.in_proj_ba", "model.language_model.layers.44.linear_attn.in_proj_b", "model.language_model.layers.44.linear_attn.in_proj_a", "model.language_model.layers.44.linear_attn.norm", "model.language_model.layers.45.input_layernorm", "model.language_model.layers.45.mlp.shared_expert_gate", "model.language_model.layers.45.post_attention_layernorm", "model.language_model.layers.45.linear_attn.A_log", "model.language_model.layers.45.linear_attn.conv1d", "model.language_model.layers.45.linear_attn.dt_bias", "model.language_model.layers.45.linear_attn.in_proj_ba", "model.language_model.layers.45.linear_attn.in_proj_b", "model.language_model.layers.45.linear_attn.in_proj_a", "model.language_model.layers.45.linear_attn.norm", "model.language_model.layers.46.input_layernorm", "model.language_model.layers.46.mlp.shared_expert_gate", "model.language_model.layers.46.post_attention_layernorm", "model.language_model.layers.46.linear_attn.A_log", "model.language_model.layers.46.linear_attn.conv1d", "model.language_model.layers.46.linear_attn.dt_bias", "model.language_model.layers.46.linear_attn.in_proj_ba", "model.language_model.layers.46.linear_attn.in_proj_b", "model.language_model.layers.46.linear_attn.in_proj_a", "model.language_model.layers.46.linear_attn.norm", "model.language_model.layers.47.input_layernorm", "model.language_model.layers.47.mlp.shared_expert_gate", "model.language_model.layers.47.post_attention_layernorm", "model.language_model.layers.47.self_attn.k_norm", "model.language_model.layers.47.self_attn.q_norm", "model.language_model.layers.48.input_layernorm", "model.language_model.layers.48.mlp.shared_expert_gate", "model.language_model.layers.48.post_attention_layernorm", "model.language_model.layers.48.linear_attn.A_log", "model.language_model.layers.48.linear_attn.conv1d", "model.language_model.layers.48.linear_attn.dt_bias", "model.language_model.layers.48.linear_attn.in_proj_ba", "model.language_model.layers.48.linear_attn.in_proj_b", "model.language_model.layers.48.linear_attn.in_proj_a", "model.language_model.layers.48.linear_attn.norm", "model.language_model.layers.49.input_layernorm", "model.language_model.layers.49.mlp.shared_expert_gate", "model.language_model.layers.49.post_attention_layernorm", "model.language_model.layers.49.linear_attn.A_log", "model.language_model.layers.49.linear_attn.conv1d", "model.language_model.layers.49.linear_attn.dt_bias", "model.language_model.layers.49.linear_attn.in_proj_ba", "model.language_model.layers.49.linear_attn.in_proj_b", "model.language_model.layers.49.linear_attn.in_proj_a", "model.language_model.layers.49.linear_attn.norm", "model.language_model.layers.50.input_layernorm", "model.language_model.layers.50.mlp.shared_expert_gate", "model.language_model.layers.50.post_attention_layernorm", "model.language_model.layers.50.linear_attn.A_log", "model.language_model.layers.50.linear_attn.conv1d", "model.language_model.layers.50.linear_attn.dt_bias", "model.language_model.layers.50.linear_attn.in_proj_ba", "model.language_model.layers.50.linear_attn.in_proj_b", "model.language_model.layers.50.linear_attn.in_proj_a", "model.language_model.layers.50.linear_attn.norm", "model.language_model.layers.51.input_layernorm", "model.language_model.layers.51.mlp.shared_expert_gate", "model.language_model.layers.51.post_attention_layernorm", "model.language_model.layers.51.self_attn.k_norm", "model.language_model.layers.51.self_attn.q_norm", "model.language_model.layers.52.input_layernorm", "model.language_model.layers.52.mlp.shared_expert_gate", "model.language_model.layers.52.post_attention_layernorm", "model.language_model.layers.52.linear_attn.A_log", "model.language_model.layers.52.linear_attn.conv1d", "model.language_model.layers.52.linear_attn.dt_bias", "model.language_model.layers.52.linear_attn.in_proj_ba", "model.language_model.layers.52.linear_attn.in_proj_b", "model.language_model.layers.52.linear_attn.in_proj_a", "model.language_model.layers.52.linear_attn.norm", "model.language_model.layers.53.input_layernorm", "model.language_model.layers.53.mlp.shared_expert_gate", "model.language_model.layers.53.post_attention_layernorm", "model.language_model.layers.53.linear_attn.A_log", "model.language_model.layers.53.linear_attn.conv1d", "model.language_model.layers.53.linear_attn.dt_bias", "model.language_model.layers.53.linear_attn.in_proj_ba", "model.language_model.layers.53.linear_attn.in_proj_b", "model.language_model.layers.53.linear_attn.in_proj_a", "model.language_model.layers.53.linear_attn.norm", "model.language_model.layers.54.input_layernorm", "model.language_model.layers.54.mlp.shared_expert_gate", "model.language_model.layers.54.post_attention_layernorm", "model.language_model.layers.54.linear_attn.A_log", "model.language_model.layers.54.linear_attn.conv1d", "model.language_model.layers.54.linear_attn.dt_bias", "model.language_model.layers.54.linear_attn.in_proj_ba", "model.language_model.layers.54.linear_attn.in_proj_b", "model.language_model.layers.54.linear_attn.in_proj_a", "model.language_model.layers.54.linear_attn.norm", "model.language_model.layers.55.input_layernorm", "model.language_model.layers.55.mlp.shared_expert_gate", "model.language_model.layers.55.post_attention_layernorm", "model.language_model.layers.55.self_attn.k_norm", "model.language_model.layers.55.self_attn.q_norm", "model.language_model.layers.56.input_layernorm", "model.language_model.layers.56.mlp.shared_expert_gate", "model.language_model.layers.56.post_attention_layernorm", "model.language_model.layers.56.linear_attn.A_log", "model.language_model.layers.56.linear_attn.conv1d", "model.language_model.layers.56.linear_attn.dt_bias", "model.language_model.layers.56.linear_attn.in_proj_ba", "model.language_model.layers.56.linear_attn.in_proj_b", "model.language_model.layers.56.linear_attn.in_proj_a", "model.language_model.layers.56.linear_attn.norm", "model.language_model.layers.57.input_layernorm", "model.language_model.layers.57.mlp.shared_expert_gate", "model.language_model.layers.57.post_attention_layernorm", "model.language_model.layers.57.linear_attn.A_log", "model.language_model.layers.57.linear_attn.conv1d", "model.language_model.layers.57.linear_attn.dt_bias", "model.language_model.layers.57.linear_attn.in_proj_ba", "model.language_model.layers.57.linear_attn.in_proj_b", "model.language_model.layers.57.linear_attn.in_proj_a", "model.language_model.layers.57.linear_attn.norm", "model.language_model.layers.58.input_layernorm", "model.language_model.layers.58.mlp.shared_expert_gate", "model.language_model.layers.58.post_attention_layernorm", "model.language_model.layers.58.linear_attn.A_log", "model.language_model.layers.58.linear_attn.conv1d", "model.language_model.layers.58.linear_attn.dt_bias", "model.language_model.layers.58.linear_attn.in_proj_ba", "model.language_model.layers.58.linear_attn.in_proj_b", "model.language_model.layers.58.linear_attn.in_proj_a", "model.language_model.layers.58.linear_attn.norm", "model.language_model.layers.59.input_layernorm", "model.language_model.layers.59.mlp.shared_expert_gate", "model.language_model.layers.59.post_attention_layernorm", "model.language_model.layers.59.self_attn.k_norm", "model.language_model.layers.59.self_attn.q_norm", "model.language_model.layers.60.input_layernorm", "model.language_model.layers.60.mlp.shared_expert_gate", "model.language_model.layers.60.post_attention_layernorm", "model.language_model.layers.60.linear_attn.A_log", "model.language_model.layers.60.linear_attn.conv1d", "model.language_model.layers.60.linear_attn.dt_bias", "model.language_model.layers.60.linear_attn.in_proj_ba", "model.language_model.layers.60.linear_attn.in_proj_b", "model.language_model.layers.60.linear_attn.in_proj_a", "model.language_model.layers.60.linear_attn.norm", "model.language_model.layers.61.input_layernorm", "model.language_model.layers.61.mlp.shared_expert_gate", "model.language_model.layers.61.post_attention_layernorm", "model.language_model.layers.61.linear_attn.A_log", "model.language_model.layers.61.linear_attn.conv1d", "model.language_model.layers.61.linear_attn.dt_bias", "model.language_model.layers.61.linear_attn.in_proj_ba", "model.language_model.layers.61.linear_attn.in_proj_b", "model.language_model.layers.61.linear_attn.in_proj_a", "model.language_model.layers.61.linear_attn.norm", "model.language_model.layers.62.input_layernorm", "model.language_model.layers.62.mlp.shared_expert_gate", "model.language_model.layers.62.post_attention_layernorm", "model.language_model.layers.62.linear_attn.A_log", "model.language_model.layers.62.linear_attn.conv1d", "model.language_model.layers.62.linear_attn.dt_bias", "model.language_model.layers.62.linear_attn.in_proj_ba", "model.language_model.layers.62.linear_attn.in_proj_b", "model.language_model.layers.62.linear_attn.in_proj_a", "model.language_model.layers.62.linear_attn.norm", "model.language_model.layers.63.input_layernorm", "model.language_model.layers.63.mlp.shared_expert_gate", "model.language_model.layers.63.post_attention_layernorm", "model.language_model.layers.63.self_attn.k_norm", "model.language_model.layers.63.self_attn.q_norm", "mtp.layers.0.input_layernorm", "mtp.layers.0.mlp.shared_expert_gate", "mtp.layers.0.post_attention_layernorm", "mtp.layers.0.self_attn.k_norm", "mtp.layers.0.self_attn.q_norm", "mtp.fc", "mtp.norm", "mtp.pre_fc_norm_embedding", "mtp.pre_fc_norm_hidden" ], "modules_to_convert": null, "activation_scheme": "dynamic", "weight_block_size": [ 128, 128 ], "dequantize": false, "scale_fmt": "float" }, "runtime_adjustments": [ { "kind": "remove_nonexistent_dense_moe_router_exclusions", "removed": [ "model.language_model.layers.0.mlp.gate", "model.language_model.layers.1.mlp.gate", "model.language_model.layers.2.mlp.gate", "model.language_model.layers.3.mlp.gate", "model.language_model.layers.4.mlp.gate", "model.language_model.layers.5.mlp.gate", "model.language_model.layers.6.mlp.gate", "model.language_model.layers.7.mlp.gate", "model.language_model.layers.8.mlp.gate", "model.language_model.layers.9.mlp.gate", "model.language_model.layers.10.mlp.gate", "model.language_model.layers.11.mlp.gate", "model.language_model.layers.12.mlp.gate", "model.language_model.layers.13.mlp.gate", "model.language_model.layers.14.mlp.gate", "model.language_model.layers.15.mlp.gate", "model.language_model.layers.16.mlp.gate", "model.language_model.layers.17.mlp.gate", "model.language_model.layers.18.mlp.gate", "model.language_model.layers.19.mlp.gate", "model.language_model.layers.20.mlp.gate", "model.language_model.layers.21.mlp.gate", "model.language_model.layers.22.mlp.gate", "model.language_model.layers.23.mlp.gate", "model.language_model.layers.24.mlp.gate", "model.language_model.layers.25.mlp.gate", "model.language_model.layers.26.mlp.gate", "model.language_model.layers.27.mlp.gate", "model.language_model.layers.28.mlp.gate", "model.language_model.layers.29.mlp.gate", "model.language_model.layers.30.mlp.gate", "model.language_model.layers.31.mlp.gate", "model.language_model.layers.32.mlp.gate", "model.language_model.layers.33.mlp.gate", "model.language_model.layers.34.mlp.gate", "model.language_model.layers.35.mlp.gate", "model.language_model.layers.36.mlp.gate", "model.language_model.layers.37.mlp.gate", "model.language_model.layers.38.mlp.gate", "model.language_model.layers.39.mlp.gate", "model.language_model.layers.40.mlp.gate", "model.language_model.layers.41.mlp.gate", "model.language_model.layers.42.mlp.gate", "model.language_model.layers.43.mlp.gate", "model.language_model.layers.44.mlp.gate", "model.language_model.layers.45.mlp.gate", "model.language_model.layers.46.mlp.gate", "model.language_model.layers.47.mlp.gate", "model.language_model.layers.48.mlp.gate", "model.language_model.layers.49.mlp.gate", "model.language_model.layers.50.mlp.gate", "model.language_model.layers.51.mlp.gate", "model.language_model.layers.52.mlp.gate", "model.language_model.layers.53.mlp.gate", "model.language_model.layers.54.mlp.gate", "model.language_model.layers.55.mlp.gate", "model.language_model.layers.56.mlp.gate", "model.language_model.layers.57.mlp.gate", "model.language_model.layers.58.mlp.gate", "model.language_model.layers.59.mlp.gate", "model.language_model.layers.60.mlp.gate", "model.language_model.layers.61.mlp.gate", "model.language_model.layers.62.mlp.gate", "model.language_model.layers.63.mlp.gate", "mtp.layers.0.mlp.gate" ], "reason": "Transformers 5.17.0 regex-prefix matching otherwise excludes gate_proj and discards its FP8 scales. Dense Qwen3.5 has no mlp.gate router. Original checkpoint bytes are unchanged." } ], "loading_info": { "missing_keys": [], "unexpected_keys": [], "mismatched_keys": [], "error_msgs": [] }, "recorder_sha256": "056ff5b7b7808a64e71e77de115948c23eff18d0e958e672141c592a3ccd8df5", "protocol_sha256": "fe0d301d853df0ee4de7e38e63e9b09a3b76f0e4570898427f7a0f2f0f13edee" }