{ "name_or_path": "tclf90/Qwen3-VL-235B-A22B-Thinking-FP8", "architectures": [ "Qwen3VLMoeForConditionalGeneration" ], "image_token_id": 151655, "model_type": "qwen3_vl_moe", "text_config": { "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 151643, "decoder_sparse_step": 1, "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, "mlp_only_layers": [], "model_type": "qwen3_vl_moe_text", "moe_intermediate_size": 1536, "norm_topk_prob": true, "num_attention_heads": 64, "num_experts": 128, "num_experts_per_tok": 8, "num_hidden_layers": 94, "num_key_value_heads": 4, "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": "4.57.0.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_moe", "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, "torch_dtype": "float16", "quantization_config": { "quant_method": "fp8", "fmt": "e4m3", "activation_scheme": "dynamic", "weight_block_size": [ 128, 128 ], "ignored_layers": ["model.language_model.layers.0.mlp.gate", "model.language_model.layers.1.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.2.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.3.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.4.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.5.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.6.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", "model.language_model.layers.64.mlp.gate", "model.language_model.layers.65.mlp.gate", "model.language_model.layers.66.mlp.gate", "model.language_model.layers.67.mlp.gate", "model.language_model.layers.68.mlp.gate", "model.language_model.layers.69.mlp.gate", "model.language_model.layers.7.mlp.gate", "model.language_model.layers.70.mlp.gate", "model.language_model.layers.71.mlp.gate", "model.language_model.layers.72.mlp.gate", "model.language_model.layers.73.mlp.gate", "model.language_model.layers.74.mlp.gate", "model.language_model.layers.75.mlp.gate", "model.language_model.layers.76.mlp.gate", "model.language_model.layers.77.mlp.gate", "model.language_model.layers.78.mlp.gate", "model.language_model.layers.79.mlp.gate", "model.language_model.layers.8.mlp.gate", "model.language_model.layers.80.mlp.gate", "model.language_model.layers.81.mlp.gate", "model.language_model.layers.82.mlp.gate", "model.language_model.layers.83.mlp.gate", "model.language_model.layers.84.mlp.gate", "model.language_model.layers.85.mlp.gate", "model.language_model.layers.86.mlp.gate", "model.language_model.layers.87.mlp.gate", "model.language_model.layers.88.mlp.gate", "model.language_model.layers.89.mlp.gate", "model.language_model.layers.9.mlp.gate", "model.language_model.layers.90.mlp.gate", "model.language_model.layers.91.mlp.gate", "model.language_model.layers.92.mlp.gate", "model.language_model.layers.93.mlp.gate", "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", "model.visual.blocks.0.norm1", "model.visual.blocks.0.norm2", "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", "model.visual.blocks.1.norm1", "model.visual.blocks.1.norm2", "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", "model.visual.blocks.10.norm1", "model.visual.blocks.10.norm2", "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", "model.visual.blocks.11.norm1", "model.visual.blocks.11.norm2", "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", "model.visual.blocks.12.norm1", "model.visual.blocks.12.norm2", "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", "model.visual.blocks.13.norm1", "model.visual.blocks.13.norm2", "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", "model.visual.blocks.14.norm1", "model.visual.blocks.14.norm2", "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", "model.visual.blocks.15.norm1", "model.visual.blocks.15.norm2", "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", "model.visual.blocks.16.norm1", "model.visual.blocks.16.norm2", "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", "model.visual.blocks.17.norm1", "model.visual.blocks.17.norm2", "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", "model.visual.blocks.18.norm1", "model.visual.blocks.18.norm2", "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", "model.visual.blocks.19.norm1", "model.visual.blocks.19.norm2", "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", "model.visual.blocks.2.norm1", "model.visual.blocks.2.norm2", "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", "model.visual.blocks.20.norm1", "model.visual.blocks.20.norm2", "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", "model.visual.blocks.21.norm1", "model.visual.blocks.21.norm2", "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", "model.visual.blocks.22.norm1", "model.visual.blocks.22.norm2", "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", "model.visual.blocks.23.norm1", "model.visual.blocks.23.norm2", "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", "model.visual.blocks.24.norm1", "model.visual.blocks.24.norm2", "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", "model.visual.blocks.25.norm1", "model.visual.blocks.25.norm2", "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", "model.visual.blocks.26.norm1", "model.visual.blocks.26.norm2", "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", "model.visual.blocks.3.norm1", "model.visual.blocks.3.norm2", "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", "model.visual.blocks.4.norm1", "model.visual.blocks.4.norm2", "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", "model.visual.blocks.5.norm1", "model.visual.blocks.5.norm2", "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", "model.visual.blocks.6.norm1", "model.visual.blocks.6.norm2", "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", "model.visual.blocks.7.norm1", "model.visual.blocks.7.norm2", "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", "model.visual.blocks.8.norm1", "model.visual.blocks.8.norm2", "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", "model.visual.blocks.9.norm1", "model.visual.blocks.9.norm2", "model.visual.deepstack_merger_list.0.linear_fc1", "model.visual.deepstack_merger_list.0.linear_fc2", "model.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", "model.visual.deepstack_merger_list.2.linear_fc1", "model.visual.deepstack_merger_list.2.linear_fc2", "model.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"] } }