gemma4:e4b-nvfp4

23.4M an hour ago

Gemma 4 models are designed to deliver frontier-level performance at each size. They are well-suited for reasoning, agentic workflows, coding, and multimodal understanding.

vision tools thinking audio cloud e2b e4b 12b 26b 31b
7bb76144da67 · 57kB
{"architectures":["Gemma4ForConditionalGeneration"],"audio_config":{"_name_or_path":"","architectures":null,"attention_chunk_size":12,"attention_context_left":13,"attention_context_right":0,"attention_invalid_logits_value":-1000000000.0,"attention_logit_cap":50.0,"chunk_size_feed_forward":0,"conv_kernel_size":5,"dtype":"bfloat16","gradient_clipping":10000000000.0,"hidden_act":"silu","hidden_size":1024,"id2label":{"0":"LABEL_0","1":"LABEL_1"},"initializer_range":0.02,"is_encoder_decoder":false,"label2id":{"LABEL_0":0,"LABEL_1":1},"model_type":"gemma4_audio","num_attention_heads":8,"num_hidden_layers":12,"output_attentions":false,"output_hidden_states":false,"output_proj_dims":1536,"problem_type":null,"residual_weight":0.5,"return_dict":true,"rms_norm_eps":1e-06,"subsampling_conv_channels":[128,32],"use_clipped_linears":true},"audio_token_id":258881,"boa_token_id":256000,"boi_token_id":255999,"dtype":"bfloat16","eoa_token_id":258883,"eoa_token_index":258883,"eoi_token_id":258882,"eos_token_id":[1,106],"image_token_id":258880,"initializer_range":0.02,"model_type":"gemma4","text_config":{"attention_bias":false,"attention_dropout":0.0,"attention_k_eq_v":false,"bos_token_id":2,"dtype":"bfloat16","enable_moe_block":false,"eos_token_id":1,"expert_intermediate_size":null,"final_logit_softcapping":30.0,"global_head_dim":512,"head_dim":256,"hidden_activation":"gelu_pytorch_tanh","hidden_size":2560,"hidden_size_per_layer_input":256,"initializer_range":0.02,"intermediate_size":10240,"layer_types":["sliding_attention","sliding_attention","sliding_attention","sliding_attention","sliding_attention","full_attention","sliding_attention","sliding_attention","sliding_attention","sliding_attention","sliding_attention","full_attention","sliding_attention","sliding_attention","sliding_attention","sliding_attention","sliding_attention","full_attention","sliding_attention","sliding_attention","sliding_attention","sliding_attention","sliding_attention","full_attention","sliding_attention","sliding_attention","sliding_attention","sliding_attention","sliding_attention","full_attention","sliding_attention","sliding_attention","sliding_attention","sliding_attention","sliding_attention","full_attention","sliding_attention","sliding_attention","sliding_attention","sliding_attention","sliding_attention","full_attention"],"max_position_embeddings":131072,"model_type":"gemma4_text","moe_intermediate_size":null,"num_attention_heads":8,"num_experts":null,"num_global_key_value_heads":null,"num_hidden_layers":42,"num_key_value_heads":2,"num_kv_shared_layers":18,"pad_token_id":0,"rms_norm_eps":1e-06,"rope_parameters":{"full_attention":{"partial_rotary_factor":0.25,"rope_theta":1000000.0,"rope_type":"proportional"},"sliding_attention":{"rope_theta":10000.0,"rope_type":"default"}},"sliding_window":512,"tie_word_embeddings":true,"top_k_experts":null,"use_bidirectional_attention":null,"use_cache":true,"use_double_wide_mlp":false,"vocab_size":262144,"vocab_size_per_layer_input":262144},"tie_word_embeddings":true,"transformers_version":"5.10.0.dev0","video_token_id":258884,"vision_config":{"_name_or_path":"","architectures":null,"attention_bias":false,"attention_dropout":0.0,"chunk_size_feed_forward":0,"default_output_length":280,"dtype":"bfloat16","global_head_dim":64,"head_dim":64,"hidden_activation":"gelu_pytorch_tanh","hidden_size":768,"id2label":{"0":"LABEL_0","1":"LABEL_1"},"initializer_range":0.02,"intermediate_size":3072,"is_encoder_decoder":false,"label2id":{"LABEL_0":0,"LABEL_1":1},"max_position_embeddings":131072,"model_type":"gemma4_vision","num_attention_heads":12,"num_hidden_layers":16,"num_key_value_heads":12,"output_attentions":false,"output_hidden_states":false,"patch_size":16,"pooling_kernel_size":3,"position_embedding_size":10240,"problem_type":null,"return_dict":true,"rms_norm_eps":1e-06,"rope_parameters":{"rope_theta":100.0,"rope_type":"default"},"standardize":false,"use_clipped_linears":true},"vision_soft_tokens_per_image":280,"quantization_config":{"config_groups":{"group_0":{"input_activations":{"dynamic":false,"num_bits":4,"type":"float","group_size":16},"weights":{"dynamic":false,"num_bits":4,"type":"float","group_size":16},"targets":["model.audio_tower.subsample_conv_projection.layer0.conv","model.audio_tower.subsample_conv_projection.layer1.conv","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.per_layer_input_gate","model.language_model.layers.0.per_layer_projection","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.per_layer_input_gate","model.language_model.layers.1.per_layer_projection","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.per_layer_input_gate","model.language_model.layers.10.per_layer_projection","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.per_layer_input_gate","model.language_model.layers.11.per_layer_projection","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.per_layer_input_gate","model.language_model.layers.12.per_layer_projection","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.per_layer_input_gate","model.language_model.layers.13.per_layer_projection","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.per_layer_input_gate","model.language_model.layers.14.per_layer_projection","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.per_layer_input_gate","model.language_model.layers.15.per_layer_projection","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.per_layer_input_gate","model.language_model.layers.16.per_layer_projection","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.per_layer_input_gate","model.language_model.layers.17.per_layer_projection","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.per_layer_input_gate","model.language_model.layers.18.per_layer_projection","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.per_layer_input_gate","model.language_model.layers.19.per_layer_projection","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.per_layer_input_gate","model.language_model.layers.2.per_layer_projection","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.per_layer_input_gate","model.language_model.layers.20.per_layer_projection","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.per_layer_input_gate","model.language_model.layers.21.per_layer_projection","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.per_layer_input_gate","model.language_model.layers.22.per_layer_projection","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.per_layer_input_gate","model.language_model.layers.23.per_layer_projection","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.per_layer_input_gate","model.language_model.layers.24.per_layer_projection","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.per_layer_input_gate","model.language_model.layers.25.per_layer_projection","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.per_layer_input_gate","model.language_model.layers.26.per_layer_projection","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.per_layer_input_gate","model.language_model.layers.27.per_layer_projection","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.per_layer_input_gate","model.language_model.layers.28.per_layer_projection","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.per_layer_input_gate","model.language_model.layers.29.per_layer_projection","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.per_layer_input_gate","model.language_model.layers.3.per_layer_projection","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.per_layer_input_gate","model.language_model.layers.30.per_layer_projection","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.per_layer_input_gate","model.language_model.layers.31.per_layer_projection","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.per_layer_input_gate","model.language_model.layers.32.per_layer_projection","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.per_layer_input_gate","model.language_model.layers.33.per_layer_projection","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.per_layer_input_gate","model.language_model.layers.34.per_layer_projection","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.per_layer_input_gate","model.language_model.layers.35.per_layer_projection","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.36.mlp.down_proj","model.language_model.layers.36.mlp.gate_proj","model.language_model.layers.36.mlp.up_proj","model.language_model.layers.36.per_layer_input_gate","model.language_model.layers.36.per_layer_projection","model.language_model.layers.36.self_attn.k_proj","model.language_model.layers.36.self_attn.o_proj","model.language_model.layers.36.self_attn.q_proj","model.language_model.layers.36.self_attn.v_proj","model.language_model.layers.37.mlp.down_proj","model.language_model.layers.37.mlp.gate_proj","model.language_model.layers.37.mlp.up_proj","model.language_model.layers.37.per_layer_input_gate","model.language_model.layers.37.per_layer_projection","model.language_model.layers.37.self_attn.k_proj","model.language_model.layers.37.self_attn.o_proj","model.language_model.layers.37.self_attn.q_proj","model.language_model.layers.37.self_attn.v_proj","model.language_model.layers.38.mlp.down_proj","model.language_model.layers.38.mlp.gate_proj","model.language_model.layers.38.mlp.up_proj","model.language_model.layers.38.per_layer_input_gate","model.language_model.layers.38.per_layer_projection","model.language_model.layers.38.self_attn.k_proj","model.language_model.layers.38.self_attn.o_proj","model.language_model.layers.38.self_attn.q_proj","model.language_model.layers.38.self_attn.v_proj","model.language_model.layers.39.mlp.down_proj","model.language_model.layers.39.mlp.gate_proj","model.language_model.layers.39.mlp.up_proj","model.language_model.layers.39.per_layer_input_gate","model.language_model.layers.39.per_layer_projection","model.language_model.layers.39.self_attn.k_proj","model.language_model.layers.39.self_attn.o_proj","model.language_model.layers.39.self_attn.q_proj","model.language_model.layers.39.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.per_layer_input_gate","model.language_model.layers.4.per_layer_projection","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.40.mlp.down_proj","model.language_model.layers.40.mlp.gate_proj","model.language_model.layers.40.mlp.up_proj","model.language_model.layers.40.per_layer_input_gate","model.language_model.layers.40.per_layer_projection","model.language_model.layers.40.self_attn.k_proj","model.language_model.layers.40.self_attn.o_proj","model.language_model.layers.40.self_attn.q_proj","model.language_model.layers.40.self_attn.v_proj","model.language_model.layers.41.mlp.down_proj","model.language_model.layers.41.mlp.gate_proj","model.language_model.layers.41.mlp.up_proj","model.language_model.layers.41.per_layer_input_gate","model.language_model.layers.41.per_layer_projection","model.language_model.layers.41.self_attn.k_proj","model.language_model.layers.41.self_attn.o_proj","model.language_model.layers.41.self_attn.q_proj","model.language_model.layers.41.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.per_layer_input_gate","model.language_model.layers.5.per_layer_projection","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.per_layer_input_gate","model.language_model.layers.6.per_layer_projection","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.per_layer_input_gate","model.language_model.layers.7.per_layer_projection","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.per_layer_input_gate","model.language_model.layers.8.per_layer_projection","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.per_layer_input_gate","model.language_model.layers.9.per_layer_projection","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","model.language_model.per_layer_model_projection"]},"group_1":{"weights":{"dynamic":false,"num_bits":4,"type":"float","group_size":16},"targets":["lm_head"]}},"quantized_layers":{"model.language_model.layers.0.self_attn.q_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.0.self_attn.k_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.0.self_attn.v_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.0.self_attn.o_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.0.mlp.gate_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.0.mlp.up_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.0.mlp.down_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.0.per_layer_input_gate":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.0.per_layer_projection":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.1.self_attn.q_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.1.self_attn.k_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.1.self_attn.v_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.1.self_attn.o_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.1.mlp.gate_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.1.mlp.up_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.1.mlp.down_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.1.per_layer_input_gate":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.1.per_layer_projection":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.2.self_attn.q_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.2.self_attn.k_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.2.self_attn.v_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.2.self_attn.o_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.2.mlp.gate_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.2.mlp.up_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.2.mlp.down_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.2.per_layer_input_gate":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.2.per_layer_projection":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.3.self_attn.q_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.3.self_attn.k_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.3.self_attn.v_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.3.self_attn.o_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.3.mlp.gate_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.3.mlp.up_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.3.mlp.down_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.3.per_layer_input_gate":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.3.per_layer_projection":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.4.self_attn.q_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.4.self_attn.k_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.4.self_attn.v_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.4.self_attn.o_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.4.mlp.gate_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.4.mlp.up_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.4.mlp.down_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.4.per_layer_input_gate":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.4.per_layer_projection":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.5.self_attn.q_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.5.self_attn.k_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.5.self_attn.v_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.5.self_attn.o_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.5.mlp.gate_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.5.mlp.up_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.5.mlp.down_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.5.per_layer_input_gate":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.5.per_layer_projection":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.6.self_attn.q_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.6.self_attn.k_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.6.self_attn.v_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.6.self_attn.o_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.6.mlp.gate_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.6.mlp.up_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.6.mlp.down_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.6.per_layer_input_gate":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.6.per_layer_projection":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.7.self_attn.q_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.7.self_attn.k_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.7.self_attn.v_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.7.self_attn.o_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.7.mlp.gate_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.7.mlp.up_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.7.mlp.down_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.7.per_layer_input_gate":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.7.per_layer_projection":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.8.self_attn.q_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.8.self_attn.k_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.8.self_attn.v_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.8.self_attn.o_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.8.mlp.gate_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.8.mlp.up_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.8.mlp.down_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.8.per_layer_input_gate":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.8.per_layer_projection":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.9.self_attn.q_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.9.self_attn.k_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.9.self_attn.v_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.9.self_attn.o_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.9.mlp.gate_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.9.mlp.up_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.9.mlp.down_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.9.per_layer_input_gate":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.9.per_layer_projection":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.10.self_attn.q_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.10.self_attn.k_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.10.self_attn.v_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.10.self_attn.o_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.10.mlp.gate_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.10.mlp.up_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.10.mlp.down_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.10.per_layer_input_gate":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.10.per_layer_projection":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.11.self_attn.q_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.11.self_attn.k_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.11.self_attn.v_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.11.self_attn.o_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.11.mlp.gate_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.11.mlp.up_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.11.mlp.down_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.11.per_layer_input_gate":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.11.per_layer_projection":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.12.self_attn.q_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.12.self_attn.k_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.12.self_attn.v_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.12.self_attn.o_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.12.mlp.gate_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.12.mlp.up_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.12.mlp.down_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.12.per_layer_input_gate":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.12.per_layer_projection":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.13.self_attn.q_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.13.self_attn.k_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.13.self_attn.v_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.13.self_attn.o_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.13.mlp.gate_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.13.mlp.up_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.13.mlp.down_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.13.per_layer_input_gate":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.13.per_layer_projection":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.14.self_attn.q_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.14.self_attn.k_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.14.self_attn.v_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.14.self_attn.o_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.14.mlp.gate_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.14.mlp.up_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.14.mlp.down_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.14.per_layer_input_gate":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.14.per_layer_projection":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.15.self_attn.q_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.15.self_attn.k_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.15.self_attn.v_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.15.self_attn.o_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.15.mlp.gate_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.15.mlp.up_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.15.mlp.down_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.15.per_layer_input_gate":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.15.per_layer_projection":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.16.self_attn.q_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.16.self_attn.k_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.16.self_attn.v_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.16.self_attn.o_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.16.mlp.gate_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.16.mlp.up_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.16.mlp.down_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.16.per_layer_input_gate":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.16.per_layer_projection":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.17.self_attn.q_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.17.self_attn.k_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.17.self_attn.v_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.17.self_attn.o_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.17.mlp.gate_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.17.mlp.up_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.17.mlp.down_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.17.per_layer_input_gate":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.17.per_layer_projection":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.18.self_attn.q_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.18.self_attn.k_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.18.self_attn.v_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.18.self_attn.o_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.18.mlp.gate_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.18.mlp.up_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.18.mlp.down_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.18.per_layer_input_gate":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.18.per_layer_projection":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.19.self_attn.q_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.19.self_attn.k_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.19.self_attn.v_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.19.self_attn.o_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.19.mlp.gate_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.19.mlp.up_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.19.mlp.down_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.19.per_layer_input_gate":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.19.per_layer_projection":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.20.self_attn.q_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.20.self_attn.k_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.20.self_attn.v_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.20.self_attn.o_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.20.mlp.gate_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.20.mlp.up_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.20.mlp.down_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.20.per_layer_input_gate":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.20.per_layer_projection":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.21.self_attn.q_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.21.self_attn.k_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.21.self_attn.v_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.21.self_attn.o_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.21.mlp.gate_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.21.mlp.up_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.21.mlp.down_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.21.per_layer_input_gate":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.21.per_layer_projection":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.22.self_attn.q_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.22.self_attn.k_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.22.self_attn.v_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.22.self_attn.o_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.22.mlp.gate_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.22.mlp.up_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.22.mlp.down_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.22.per_layer_input_gate":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.22.per_layer_projection":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.23.self_attn.q_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.23.self_attn.k_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.23.self_attn.v_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.23.self_attn.o_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.23.mlp.gate_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.23.mlp.up_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.23.mlp.down_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.23.per_layer_input_gate":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.23.per_layer_projection":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.24.self_attn.q_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.24.self_attn.k_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.24.self_attn.v_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.24.self_attn.o_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.24.mlp.gate_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.24.mlp.up_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.24.mlp.down_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.24.per_layer_input_gate":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.24.per_layer_projection":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.25.self_attn.q_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.25.self_attn.k_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.25.self_attn.v_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.25.self_attn.o_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.25.mlp.gate_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.25.mlp.up_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.25.mlp.down_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.25.per_layer_input_gate":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.25.per_layer_projection":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.26.self_attn.q_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.26.self_attn.k_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.26.self_attn.v_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.26.self_attn.o_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.26.mlp.gate_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.26.mlp.up_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.26.mlp.down_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.26.per_layer_input_gate":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.26.per_layer_projection":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.27.self_attn.q_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.27.self_attn.k_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.27.self_attn.v_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.27.self_attn.o_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.27.mlp.gate_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.27.mlp.up_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.27.mlp.down_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.27.per_layer_input_gate":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.27.per_layer_projection":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.28.self_attn.q_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.28.self_attn.k_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.28.self_attn.v_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.28.self_attn.o_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.28.mlp.gate_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.28.mlp.up_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.28.mlp.down_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.28.per_layer_input_gate":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.28.per_layer_projection":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.29.self_attn.q_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.29.self_attn.k_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.29.self_attn.v_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.29.self_attn.o_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.29.mlp.gate_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.29.mlp.up_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.29.mlp.down_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.29.per_layer_input_gate":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.29.per_layer_projection":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.30.self_attn.q_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.30.self_attn.k_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.30.self_attn.v_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.30.self_attn.o_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.30.mlp.gate_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.30.mlp.up_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.30.mlp.down_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.30.per_layer_input_gate":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.30.per_layer_projection":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.31.self_attn.q_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.31.self_attn.k_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.31.self_attn.v_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.31.self_attn.o_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.31.mlp.gate_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.31.mlp.up_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.31.mlp.down_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.31.per_layer_input_gate":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.31.per_layer_projection":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.32.self_attn.q_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.32.self_attn.k_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.32.self_attn.v_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.32.self_attn.o_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.32.mlp.gate_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.32.mlp.up_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.32.mlp.down_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.32.per_layer_input_gate":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.32.per_layer_projection":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.33.self_attn.q_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.33.self_attn.k_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.33.self_attn.v_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.33.self_attn.o_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.33.mlp.gate_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.33.mlp.up_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.33.mlp.down_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.33.per_layer_input_gate":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.33.per_layer_projection":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.34.self_attn.q_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.34.self_attn.k_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.34.self_attn.v_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.34.self_attn.o_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.34.mlp.gate_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.34.mlp.up_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.34.mlp.down_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.34.per_layer_input_gate":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.34.per_layer_projection":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.35.self_attn.q_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.35.self_attn.k_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.35.self_attn.v_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.35.self_attn.o_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.35.mlp.gate_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.35.mlp.up_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.35.mlp.down_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.35.per_layer_input_gate":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.35.per_layer_projection":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.36.self_attn.q_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.36.self_attn.k_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.36.self_attn.v_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.36.self_attn.o_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.36.mlp.gate_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.36.mlp.up_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.36.mlp.down_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.36.per_layer_input_gate":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.36.per_layer_projection":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.37.self_attn.q_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.37.self_attn.k_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.37.self_attn.v_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.37.self_attn.o_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.37.mlp.gate_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.37.mlp.up_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.37.mlp.down_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.37.per_layer_input_gate":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.37.per_layer_projection":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.38.self_attn.q_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.38.self_attn.k_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.38.self_attn.v_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.38.self_attn.o_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.38.mlp.gate_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.38.mlp.up_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.38.mlp.down_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.38.per_layer_input_gate":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.38.per_layer_projection":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.39.self_attn.q_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.39.self_attn.k_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.39.self_attn.v_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.39.self_attn.o_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.39.mlp.gate_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.39.mlp.up_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.39.mlp.down_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.39.per_layer_input_gate":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.39.per_layer_projection":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.40.self_attn.q_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.40.self_attn.k_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.40.self_attn.v_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.40.self_attn.o_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.40.mlp.gate_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.40.mlp.up_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.40.mlp.down_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.40.per_layer_input_gate":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.40.per_layer_projection":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.41.self_attn.q_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.41.self_attn.k_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.41.self_attn.v_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.41.self_attn.o_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.41.mlp.gate_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.41.mlp.up_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.41.mlp.down_proj":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.41.per_layer_input_gate":{"quant_algo":"NVFP4","group_size":16},"model.language_model.layers.41.per_layer_projection":{"quant_algo":"NVFP4","group_size":16},"model.language_model.per_layer_model_projection":{"quant_algo":"NVFP4","group_size":16},"model.audio_tower.subsample_conv_projection.layer0.conv":{"quant_algo":"NVFP4","group_size":16},"model.audio_tower.subsample_conv_projection.layer1.conv":{"quant_algo":"NVFP4","group_size":16},"lm_head":{"quant_algo":"W4A16_NVFP4","group_size":16}},"ignore":[],"quant_algo":"MIXED_PRECISION","kv_cache_scheme":{"dynamic":false,"num_bits":8,"type":"float"},"producer":{"name":"modelopt","version":"0.45.0.dev110+g04f58166a"},"quant_method":"modelopt"}}