| { | |
| "architectures": [ | |
| "Qwen3_5ForConditionalGeneration" | |
| ], | |
| "dtype": "bfloat16", | |
| "image_token_id": 248056, | |
| "language_model_only": false, | |
| "model_type": "qwen3_5", | |
| "text_config": { | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "attn_output_gate": true, | |
| "bos_token_id": 248044, | |
| "dtype": "bfloat16", | |
| "eos_token_id": 248044, | |
| "full_attention_interval": 4, | |
| "head_dim": 256, | |
| "hidden_act": "silu", | |
| "hidden_size": 5120, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 17408, | |
| "layer_types": [ | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention" | |
| ], | |
| "linear_conv_kernel_dim": 4, | |
| "linear_key_head_dim": 128, | |
| "linear_num_key_heads": 16, | |
| "linear_num_value_heads": 48, | |
| "linear_value_head_dim": 128, | |
| "mamba_ssm_dtype": "float32", | |
| "max_position_embeddings": 262144, | |
| "model_type": "qwen3_5_text", | |
| "mtp_num_hidden_layers": 0, | |
| "mtp_use_dedicated_embeddings": false, | |
| "num_attention_heads": 24, | |
| "num_hidden_layers": 64, | |
| "num_key_value_heads": 4, | |
| "output_gate_type": "swish", | |
| "pad_token_id": null, | |
| "partial_rotary_factor": 0.25, | |
| "rms_norm_eps": 1e-06, | |
| "rope_parameters": { | |
| "mrope_interleaved": true, | |
| "mrope_section": [ | |
| 11, | |
| 11, | |
| 10 | |
| ], | |
| "partial_rotary_factor": 0.25, | |
| "rope_theta": 10000000, | |
| "rope_type": "default" | |
| }, | |
| "tie_word_embeddings": false, | |
| "use_cache": false, | |
| "vocab_size": 248320 | |
| }, | |
| "tie_word_embeddings": false, | |
| "transformers_version": "5.17.0", | |
| "use_cache": false, | |
| "video_token_id": 248057, | |
| "vision_config": { | |
| "deepstack_visual_indexes": [], | |
| "depth": 27, | |
| "dtype": "bfloat16", | |
| "hidden_act": "gelu_pytorch_tanh", | |
| "hidden_size": 1152, | |
| "in_channels": 3, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 4304, | |
| "model_type": "qwen3_5_vision", | |
| "num_heads": 16, | |
| "num_position_embeddings": 2304, | |
| "out_hidden_size": 5120, | |
| "patch_size": 16, | |
| "rope_parameters": { | |
| "rope_theta": 10000.0, | |
| "rope_type": "axial" | |
| }, | |
| "spatial_merge_size": 2, | |
| "temporal_patch_size": 2 | |
| }, | |
| "vision_end_token_id": 248054, | |
| "vision_start_token_id": 248053, | |
| "quantization_config": { | |
| "quant_method": "compressed-tensors", | |
| "format": "int-quantized", | |
| "quantization_status": "compressed", | |
| "config_groups": { | |
| "group_0": { | |
| "targets": [ | |
| "Linear" | |
| ], | |
| "weights": { | |
| "num_bits": 8, | |
| "type": "int", | |
| "symmetric": true, | |
| "strategy": "channel", | |
| "dynamic": false | |
| }, | |
| "input_activations": { | |
| "num_bits": 8, | |
| "type": "int", | |
| "symmetric": true, | |
| "strategy": "token", | |
| "dynamic": true | |
| } | |
| } | |
| }, | |
| "ignore": [ | |
| "lm_head", | |
| "model.language_model.embed_tokens", | |
| "model.language_model.layers.0.input_layernorm", | |
| "model.language_model.layers.0.linear_attn.conv1d", | |
| "model.language_model.layers.0.linear_attn.in_proj_a", | |
| "model.language_model.layers.0.linear_attn.in_proj_b", | |
| "model.language_model.layers.0.linear_attn.norm", | |
| "model.language_model.layers.0.post_attention_layernorm", | |
| "model.language_model.layers.1.input_layernorm", | |
| "model.language_model.layers.1.linear_attn.conv1d", | |
| "model.language_model.layers.1.linear_attn.in_proj_a", | |
| "model.language_model.layers.1.linear_attn.in_proj_b", | |
| "model.language_model.layers.1.linear_attn.norm", | |
| "model.language_model.layers.1.post_attention_layernorm", | |
| "model.language_model.layers.10.input_layernorm", | |
| "model.language_model.layers.10.linear_attn.conv1d", | |
| "model.language_model.layers.10.linear_attn.in_proj_a", | |
| "model.language_model.layers.10.linear_attn.in_proj_b", | |
| "model.language_model.layers.10.linear_attn.norm", | |
| "model.language_model.layers.10.post_attention_layernorm", | |
| "model.language_model.layers.11.input_layernorm", | |
| "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.linear_attn.conv1d", | |
| "model.language_model.layers.12.linear_attn.in_proj_a", | |
| "model.language_model.layers.12.linear_attn.in_proj_b", | |
| "model.language_model.layers.12.linear_attn.norm", | |
| "model.language_model.layers.12.post_attention_layernorm", | |
| "model.language_model.layers.13.input_layernorm", | |
| "model.language_model.layers.13.linear_attn.conv1d", | |
| "model.language_model.layers.13.linear_attn.in_proj_a", | |
| "model.language_model.layers.13.linear_attn.in_proj_b", | |
| "model.language_model.layers.13.linear_attn.norm", | |
| "model.language_model.layers.13.post_attention_layernorm", | |
| "model.language_model.layers.14.input_layernorm", | |
| "model.language_model.layers.14.linear_attn.conv1d", | |
| "model.language_model.layers.14.linear_attn.in_proj_a", | |
| "model.language_model.layers.14.linear_attn.in_proj_b", | |
| "model.language_model.layers.14.linear_attn.norm", | |
| "model.language_model.layers.14.post_attention_layernorm", | |
| "model.language_model.layers.15.input_layernorm", | |
| "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.linear_attn.conv1d", | |
| "model.language_model.layers.16.linear_attn.in_proj_a", | |
| "model.language_model.layers.16.linear_attn.in_proj_b", | |
| "model.language_model.layers.16.linear_attn.norm", | |
| "model.language_model.layers.16.post_attention_layernorm", | |
| "model.language_model.layers.17.input_layernorm", | |
| "model.language_model.layers.17.linear_attn.conv1d", | |
| "model.language_model.layers.17.linear_attn.in_proj_a", | |
| "model.language_model.layers.17.linear_attn.in_proj_b", | |
| "model.language_model.layers.17.linear_attn.norm", | |
| "model.language_model.layers.17.post_attention_layernorm", | |
| "model.language_model.layers.18.input_layernorm", | |
| "model.language_model.layers.18.linear_attn.conv1d", | |
| "model.language_model.layers.18.linear_attn.in_proj_a", | |
| "model.language_model.layers.18.linear_attn.in_proj_b", | |
| "model.language_model.layers.18.linear_attn.norm", | |
| "model.language_model.layers.18.post_attention_layernorm", | |
| "model.language_model.layers.19.input_layernorm", | |
| "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.2.input_layernorm", | |
| "model.language_model.layers.2.linear_attn.conv1d", | |
| "model.language_model.layers.2.linear_attn.in_proj_a", | |
| "model.language_model.layers.2.linear_attn.in_proj_b", | |
| "model.language_model.layers.2.linear_attn.norm", | |
| "model.language_model.layers.2.post_attention_layernorm", | |
| "model.language_model.layers.20.input_layernorm", | |
| "model.language_model.layers.20.linear_attn.conv1d", | |
| "model.language_model.layers.20.linear_attn.in_proj_a", | |
| "model.language_model.layers.20.linear_attn.in_proj_b", | |
| "model.language_model.layers.20.linear_attn.norm", | |
| "model.language_model.layers.20.post_attention_layernorm", | |
| "model.language_model.layers.21.input_layernorm", | |
| "model.language_model.layers.21.linear_attn.conv1d", | |
| "model.language_model.layers.21.linear_attn.in_proj_a", | |
| "model.language_model.layers.21.linear_attn.in_proj_b", | |
| "model.language_model.layers.21.linear_attn.norm", | |
| "model.language_model.layers.21.post_attention_layernorm", | |
| "model.language_model.layers.22.input_layernorm", | |
| "model.language_model.layers.22.linear_attn.conv1d", | |
| "model.language_model.layers.22.linear_attn.in_proj_a", | |
| "model.language_model.layers.22.linear_attn.in_proj_b", | |
| "model.language_model.layers.22.linear_attn.norm", | |
| "model.language_model.layers.22.post_attention_layernorm", | |
| "model.language_model.layers.23.input_layernorm", | |
| "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.linear_attn.conv1d", | |
| "model.language_model.layers.24.linear_attn.in_proj_a", | |
| "model.language_model.layers.24.linear_attn.in_proj_b", | |
| "model.language_model.layers.24.linear_attn.norm", | |
| "model.language_model.layers.24.post_attention_layernorm", | |
| "model.language_model.layers.25.input_layernorm", | |
| "model.language_model.layers.25.linear_attn.conv1d", | |
| "model.language_model.layers.25.linear_attn.in_proj_a", | |
| "model.language_model.layers.25.linear_attn.in_proj_b", | |
| "model.language_model.layers.25.linear_attn.norm", | |
| "model.language_model.layers.25.post_attention_layernorm", | |
| "model.language_model.layers.26.input_layernorm", | |
| "model.language_model.layers.26.linear_attn.conv1d", | |
| "model.language_model.layers.26.linear_attn.in_proj_a", | |
| "model.language_model.layers.26.linear_attn.in_proj_b", | |
| "model.language_model.layers.26.linear_attn.norm", | |
| "model.language_model.layers.26.post_attention_layernorm", | |
| "model.language_model.layers.27.input_layernorm", | |
| "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.linear_attn.conv1d", | |
| "model.language_model.layers.28.linear_attn.in_proj_a", | |
| "model.language_model.layers.28.linear_attn.in_proj_b", | |
| "model.language_model.layers.28.linear_attn.norm", | |
| "model.language_model.layers.28.post_attention_layernorm", | |
| "model.language_model.layers.29.input_layernorm", | |
| "model.language_model.layers.29.linear_attn.conv1d", | |
| "model.language_model.layers.29.linear_attn.in_proj_a", | |
| "model.language_model.layers.29.linear_attn.in_proj_b", | |
| "model.language_model.layers.29.linear_attn.norm", | |
| "model.language_model.layers.29.post_attention_layernorm", | |
| "model.language_model.layers.3.input_layernorm", | |
| "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.30.input_layernorm", | |
| "model.language_model.layers.30.linear_attn.conv1d", | |
| "model.language_model.layers.30.linear_attn.in_proj_a", | |
| "model.language_model.layers.30.linear_attn.in_proj_b", | |
| "model.language_model.layers.30.linear_attn.norm", | |
| "model.language_model.layers.30.post_attention_layernorm", | |
| "model.language_model.layers.31.input_layernorm", | |
| "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.linear_attn.conv1d", | |
| "model.language_model.layers.32.linear_attn.in_proj_a", | |
| "model.language_model.layers.32.linear_attn.in_proj_b", | |
| "model.language_model.layers.32.linear_attn.norm", | |
| "model.language_model.layers.32.post_attention_layernorm", | |
| "model.language_model.layers.33.input_layernorm", | |
| "model.language_model.layers.33.linear_attn.conv1d", | |
| "model.language_model.layers.33.linear_attn.in_proj_a", | |
| "model.language_model.layers.33.linear_attn.in_proj_b", | |
| "model.language_model.layers.33.linear_attn.norm", | |
| "model.language_model.layers.33.post_attention_layernorm", | |
| "model.language_model.layers.34.input_layernorm", | |
| "model.language_model.layers.34.linear_attn.conv1d", | |
| "model.language_model.layers.34.linear_attn.in_proj_a", | |
| "model.language_model.layers.34.linear_attn.in_proj_b", | |
| "model.language_model.layers.34.linear_attn.norm", | |
| "model.language_model.layers.34.post_attention_layernorm", | |
| "model.language_model.layers.35.input_layernorm", | |
| "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.linear_attn.conv1d", | |
| "model.language_model.layers.36.linear_attn.in_proj_a", | |
| "model.language_model.layers.36.linear_attn.in_proj_b", | |
| "model.language_model.layers.36.linear_attn.norm", | |
| "model.language_model.layers.36.post_attention_layernorm", | |
| "model.language_model.layers.37.input_layernorm", | |
| "model.language_model.layers.37.linear_attn.conv1d", | |
| "model.language_model.layers.37.linear_attn.in_proj_a", | |
| "model.language_model.layers.37.linear_attn.in_proj_b", | |
| "model.language_model.layers.37.linear_attn.norm", | |
| "model.language_model.layers.37.post_attention_layernorm", | |
| "model.language_model.layers.38.input_layernorm", | |
| "model.language_model.layers.38.linear_attn.conv1d", | |
| "model.language_model.layers.38.linear_attn.in_proj_a", | |
| "model.language_model.layers.38.linear_attn.in_proj_b", | |
| "model.language_model.layers.38.linear_attn.norm", | |
| "model.language_model.layers.38.post_attention_layernorm", | |
| "model.language_model.layers.39.input_layernorm", | |
| "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.4.input_layernorm", | |
| "model.language_model.layers.4.linear_attn.conv1d", | |
| "model.language_model.layers.4.linear_attn.in_proj_a", | |
| "model.language_model.layers.4.linear_attn.in_proj_b", | |
| "model.language_model.layers.4.linear_attn.norm", | |
| "model.language_model.layers.4.post_attention_layernorm", | |
| "model.language_model.layers.40.input_layernorm", | |
| "model.language_model.layers.40.linear_attn.conv1d", | |
| "model.language_model.layers.40.linear_attn.in_proj_a", | |
| "model.language_model.layers.40.linear_attn.in_proj_b", | |
| "model.language_model.layers.40.linear_attn.norm", | |
| "model.language_model.layers.40.post_attention_layernorm", | |
| "model.language_model.layers.41.input_layernorm", | |
| "model.language_model.layers.41.linear_attn.conv1d", | |
| "model.language_model.layers.41.linear_attn.in_proj_a", | |
| "model.language_model.layers.41.linear_attn.in_proj_b", | |
| "model.language_model.layers.41.linear_attn.norm", | |
| "model.language_model.layers.41.post_attention_layernorm", | |
| "model.language_model.layers.42.input_layernorm", | |
| "model.language_model.layers.42.linear_attn.conv1d", | |
| "model.language_model.layers.42.linear_attn.in_proj_a", | |
| "model.language_model.layers.42.linear_attn.in_proj_b", | |
| "model.language_model.layers.42.linear_attn.norm", | |
| "model.language_model.layers.42.post_attention_layernorm", | |
| "model.language_model.layers.43.input_layernorm", | |
| "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.linear_attn.conv1d", | |
| "model.language_model.layers.44.linear_attn.in_proj_a", | |
| "model.language_model.layers.44.linear_attn.in_proj_b", | |
| "model.language_model.layers.44.linear_attn.norm", | |
| "model.language_model.layers.44.post_attention_layernorm", | |
| "model.language_model.layers.45.input_layernorm", | |
| "model.language_model.layers.45.linear_attn.conv1d", | |
| "model.language_model.layers.45.linear_attn.in_proj_a", | |
| "model.language_model.layers.45.linear_attn.in_proj_b", | |
| "model.language_model.layers.45.linear_attn.norm", | |
| "model.language_model.layers.45.post_attention_layernorm", | |
| "model.language_model.layers.46.input_layernorm", | |
| "model.language_model.layers.46.linear_attn.conv1d", | |
| "model.language_model.layers.46.linear_attn.in_proj_a", | |
| "model.language_model.layers.46.linear_attn.in_proj_b", | |
| "model.language_model.layers.46.linear_attn.norm", | |
| "model.language_model.layers.46.post_attention_layernorm", | |
| "model.language_model.layers.47.input_layernorm", | |
| "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.linear_attn.conv1d", | |
| "model.language_model.layers.48.linear_attn.in_proj_a", | |
| "model.language_model.layers.48.linear_attn.in_proj_b", | |
| "model.language_model.layers.48.linear_attn.norm", | |
| "model.language_model.layers.48.post_attention_layernorm", | |
| "model.language_model.layers.49.input_layernorm", | |
| "model.language_model.layers.49.linear_attn.conv1d", | |
| "model.language_model.layers.49.linear_attn.in_proj_a", | |
| "model.language_model.layers.49.linear_attn.in_proj_b", | |
| "model.language_model.layers.49.linear_attn.norm", | |
| "model.language_model.layers.49.post_attention_layernorm", | |
| "model.language_model.layers.5.input_layernorm", | |
| "model.language_model.layers.5.linear_attn.conv1d", | |
| "model.language_model.layers.5.linear_attn.in_proj_a", | |
| "model.language_model.layers.5.linear_attn.in_proj_b", | |
| "model.language_model.layers.5.linear_attn.norm", | |
| "model.language_model.layers.5.post_attention_layernorm", | |
| "model.language_model.layers.50.input_layernorm", | |
| "model.language_model.layers.50.linear_attn.conv1d", | |
| "model.language_model.layers.50.linear_attn.in_proj_a", | |
| "model.language_model.layers.50.linear_attn.in_proj_b", | |
| "model.language_model.layers.50.linear_attn.norm", | |
| "model.language_model.layers.50.post_attention_layernorm", | |
| "model.language_model.layers.51.input_layernorm", | |
| "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.linear_attn.conv1d", | |
| "model.language_model.layers.52.linear_attn.in_proj_a", | |
| "model.language_model.layers.52.linear_attn.in_proj_b", | |
| "model.language_model.layers.52.linear_attn.norm", | |
| "model.language_model.layers.52.post_attention_layernorm", | |
| "model.language_model.layers.53.input_layernorm", | |
| "model.language_model.layers.53.linear_attn.conv1d", | |
| "model.language_model.layers.53.linear_attn.in_proj_a", | |
| "model.language_model.layers.53.linear_attn.in_proj_b", | |
| "model.language_model.layers.53.linear_attn.norm", | |
| "model.language_model.layers.53.post_attention_layernorm", | |
| "model.language_model.layers.54.input_layernorm", | |
| "model.language_model.layers.54.linear_attn.conv1d", | |
| "model.language_model.layers.54.linear_attn.in_proj_a", | |
| "model.language_model.layers.54.linear_attn.in_proj_b", | |
| "model.language_model.layers.54.linear_attn.norm", | |
| "model.language_model.layers.54.post_attention_layernorm", | |
| "model.language_model.layers.55.input_layernorm", | |
| "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.linear_attn.conv1d", | |
| "model.language_model.layers.56.linear_attn.in_proj_a", | |
| "model.language_model.layers.56.linear_attn.in_proj_b", | |
| "model.language_model.layers.56.linear_attn.norm", | |
| "model.language_model.layers.56.post_attention_layernorm", | |
| "model.language_model.layers.57.input_layernorm", | |
| "model.language_model.layers.57.linear_attn.conv1d", | |
| "model.language_model.layers.57.linear_attn.in_proj_a", | |
| "model.language_model.layers.57.linear_attn.in_proj_b", | |
| "model.language_model.layers.57.linear_attn.norm", | |
| "model.language_model.layers.57.post_attention_layernorm", | |
| "model.language_model.layers.58.input_layernorm", | |
| "model.language_model.layers.58.linear_attn.conv1d", | |
| "model.language_model.layers.58.linear_attn.in_proj_a", | |
| "model.language_model.layers.58.linear_attn.in_proj_b", | |
| "model.language_model.layers.58.linear_attn.norm", | |
| "model.language_model.layers.58.post_attention_layernorm", | |
| "model.language_model.layers.59.input_layernorm", | |
| "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.6.input_layernorm", | |
| "model.language_model.layers.6.linear_attn.conv1d", | |
| "model.language_model.layers.6.linear_attn.in_proj_a", | |
| "model.language_model.layers.6.linear_attn.in_proj_b", | |
| "model.language_model.layers.6.linear_attn.norm", | |
| "model.language_model.layers.6.post_attention_layernorm", | |
| "model.language_model.layers.60.input_layernorm", | |
| "model.language_model.layers.60.linear_attn.conv1d", | |
| "model.language_model.layers.60.linear_attn.in_proj_a", | |
| "model.language_model.layers.60.linear_attn.in_proj_b", | |
| "model.language_model.layers.60.linear_attn.norm", | |
| "model.language_model.layers.60.post_attention_layernorm", | |
| "model.language_model.layers.61.input_layernorm", | |
| "model.language_model.layers.61.linear_attn.conv1d", | |
| "model.language_model.layers.61.linear_attn.in_proj_a", | |
| "model.language_model.layers.61.linear_attn.in_proj_b", | |
| "model.language_model.layers.61.linear_attn.norm", | |
| "model.language_model.layers.61.post_attention_layernorm", | |
| "model.language_model.layers.62.input_layernorm", | |
| "model.language_model.layers.62.linear_attn.conv1d", | |
| "model.language_model.layers.62.linear_attn.in_proj_a", | |
| "model.language_model.layers.62.linear_attn.in_proj_b", | |
| "model.language_model.layers.62.linear_attn.norm", | |
| "model.language_model.layers.62.post_attention_layernorm", | |
| "model.language_model.layers.63.input_layernorm", | |
| "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", | |
| "model.language_model.layers.7.input_layernorm", | |
| "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.linear_attn.conv1d", | |
| "model.language_model.layers.8.linear_attn.in_proj_a", | |
| "model.language_model.layers.8.linear_attn.in_proj_b", | |
| "model.language_model.layers.8.linear_attn.norm", | |
| "model.language_model.layers.8.post_attention_layernorm", | |
| "model.language_model.layers.9.input_layernorm", | |
| "model.language_model.layers.9.linear_attn.conv1d", | |
| "model.language_model.layers.9.linear_attn.in_proj_a", | |
| "model.language_model.layers.9.linear_attn.in_proj_b", | |
| "model.language_model.layers.9.linear_attn.norm", | |
| "model.language_model.layers.9.post_attention_layernorm", | |
| "model.language_model.norm", | |
| "re:.*visual.*" | |
| ] | |
| } | |
| } | |
Xet Storage Details
- Size:
- 25.6 kB
- Xet hash:
- 75d09d36933550e8858f8f70342c0c15cf41eaba99da17790fff44fef26d6962
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.