GitHub
187K
Download
Models
Docs
Pricing
Sign in
Download
Models
Docs
Pricing
Sign in
dhiltgen
/
qwen3.8-flash-next
:125b-a6b-nvfp4
30
Downloads
Updated
1 week ago
Cancel
vision
tools
thinking
qwen3.8-flash-next:125b-a6b-nvfp4
...
/
json
a3bd0c94db4e ยท 181kB
{
"architectures": [
"Qwen4ExpForConditionalGeneration"
],
"image_token_id": 248056,
"language_model_only": false,
"model_type": "qwen4_exp",
"text_config": {
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 248044,
"dtype": "bfloat16",
"eos_token_id": 248044,
"full_attention_interval": 4,
"hc_count": 4,
"hc_lowrank": 320,
"head_dim": 256,
"heads_per_ngram": 8,
"hidden_act": "silu",
"hidden_size": 2560,
"indexer_budget": 2048,
"indexer_compress_ratio": 4,
"indexer_head_dim": 128,
"indexer_kv_heads": 1,
"indexer_n_heads": 4,
"initializer_range": 0.02,
"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_conv_kernel_dim": 4,
"linear_key_head_dim": 128,
"linear_num_key_heads": 16,
"linear_num_value_heads": 48,
"linear_value_head_dim": 128,
"make_ngram_vocab_size_divisible_by": 128,
"mamba_ssm_dtype": "float32",
"max_position_embeddings": 262144,
"model_type": "qwen4_exp_text",
"moe_intermediate_size": 640,
"mtp": {
"hybrid": true,
"layer_types": [
"full_attention"
],
"mtp_use_hidden_state_from_layer": null,
"num_hidden_layers": 1,
"rope_theta": 10000000
},
"mtp_num_hidden_layers": 1,
"mtp_use_dedicated_embeddings": false,
"ngram_size": 3,
"ngram_vocab_size_base": 20000000,
"num_attention_heads": 24,
"num_experts": 512,
"num_experts_per_tok": 10,
"num_hidden_layers": 48,
"num_key_value_heads": 2,
"output_gate_type": "sigmoid",
"output_router_logits": false,
"pad_token_id": null,
"partial_rotary_factor": 0.25,
"ple_conv_kernel_size": 4,
"ple_embed_dim": 2560,
"ple_layer_ids": [
2
],
"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"
},
"router_aux_loss_coef": 0.001,
"shared_expert_intermediate_size": 640,
"split_ngram_parts": 128,
"tie_word_embeddings": false,
"use_cache": true,
"vocab_size": 248320
},
"tie_word_embeddings": false,
"transformers_version": "5.8.0.dev0",
"video_token_id": 248057,
"vision_config": {
"deepstack_visual_indexes": [],
"depth": 27,
"hidden_act": "gelu_pytorch_tanh",
"hidden_size": 1152,
"in_channels": 3,
"initializer_range": 0.02,
"intermediate_size": 4304,
"model_type": "qwen4_exp",
"num_heads": 16,
"num_position_embeddings": 2304,
"out_hidden_size": 2560,
"patch_size": 16,
"spatial_merge_size": 2,
"temporal_patch_size": 2
},
"vision_end_token_id": 248054,
"vision_start_token_id": 248053,
"quantization_config": {
"config_groups": {
"group_0": {
"input_activations": {
"dynamic": true,
"num_bits": 8,
"type": "float",
"group_size": 32,
"strategy": "group"
},
"weights": {
"dynamic": false,
"num_bits": 8,
"type": "float",
"group_size": 32,
"strategy": "group"
},
"targets": [
"lm_head",
"model.language_model.embed_tokens",
"model.language_model.hyper_connection_mixer.input_mix_weight_down",
"model.language_model.hyper_connection_mixer.input_mix_weight_up",
"model.language_model.layers.0.attn_hyper_connection.block_inject_weight",
"model.language_model.layers.0.attn_hyper_connection.input_mix_weight_down",
"model.language_model.layers.0.attn_hyper_connection.input_mix_weight_up",
"model.language_model.layers.0.linear_attn.in_proj_qkv",
"model.language_model.layers.0.linear_attn.in_proj_z",
"model.language_model.layers.0.linear_attn.out_proj",
"model.language_model.layers.0.mlp.shared_expert.down_proj",
"model.language_model.layers.0.mlp.shared_expert.gate_proj",
"model.language_model.layers.0.mlp.shared_expert.up_proj",
"model.language_model.layers.0.mlp_hyper_connection.block_inject_weight",
"model.language_model.layers.0.mlp_hyper_connection.input_mix_weight_down",
"model.language_model.layers.0.mlp_hyper_connection.input_mix_weight_up",
"model.language_model.layers.1.attn_hyper_connection.block_inject_weight",
"model.language_model.layers.1.attn_hyper_connection.input_mix_weight_down",
"model.language_model.layers.1.attn_hyper_connection.input_mix_weight_up",
"model.language_model.layers.1.linear_attn.in_proj_qkv",
"model.language_model.layers.1.linear_attn.in_proj_z",
"model.language_model.layers.1.linear_attn.out_proj",
"model.language_model.layers.1.mlp.shared_expert.down_proj",
"model.language_model.layers.1.mlp.shared_expert.gate_proj",
"model.language_model.layers.1.mlp.shared_expert.up_proj",
"model.language_model.layers.1.mlp_hyper_connection.block_inject_weight",
"model.language_model.layers.1.mlp_hyper_connection.input_mix_weight_down",
"model.language_model.layers.1.mlp_hyper_connection.input_mix_weight_up",
"model.language_model.layers.1.ple.key_proj",
"model.language_model.layers.1.ple.value_proj",
"model.language_model.layers.10.attn_hyper_connection.block_inject_weight",
"model.language_model.layers.10.attn_hyper_connection.input_mix_weight_down",
"model.language_model.layers.10.attn_hyper_connection.input_mix_weight_up",
"model.language_model.layers.10.linear_attn.in_proj_qkv",
"model.language_model.layers.10.linear_attn.in_proj_z",
"model.language_model.layers.10.linear_attn.out_proj",
"model.language_model.layers.10.mlp.shared_expert.down_proj",
"model.language_model.layers.10.mlp.shared_expert.gate_proj",
"model.language_model.layers.10.mlp.shared_expert.up_proj",
"model.language_model.layers.10.mlp_hyper_connection.block_inject_weight",
"model.language_model.layers.10.mlp_hyper_connection.input_mix_weight_down",
"model.language_model.layers.10.mlp_hyper_connection.input_mix_weight_up",
"model.language_model.layers.11.attn_hyper_connection.block_inject_weight",
"model.language_model.layers.11.attn_hyper_connection.input_mix_weight_down",
"model.language_model.layers.11.attn_hyper_connection.input_mix_weight_up",
"model.language_model.layers.11.mlp.shared_expert.down_proj",
"model.language_model.layers.11.mlp.shared_expert.gate_proj",
"model.language_model.layers.11.mlp.shared_expert.up_proj",
"model.language_model.layers.11.mlp_hyper_connection.block_inject_weight",
"model.language_model.layers.11.mlp_hyper_connection.input_mix_weight_down",
"model.language_model.layers.11.mlp_hyper_connection.input_mix_weight_up",
"model.language_model.layers.11.self_attn.o_proj",
"model.language_model.layers.12.attn_hyper_connection.block_inject_weight",
"model.language_model.layers.12.attn_hyper_connection.input_mix_weight_down",
"model.language_model.layers.12.attn_hyper_connection.input_mix_weight_up",
"model.language_model.layers.12.linear_attn.in_proj_qkv",
"model.language_model.layers.12.linear_attn.in_proj_z",
"model.language_model.layers.12.linear_attn.out_proj",
"model.language_model.layers.12.mlp.shared_expert.down_proj",
"model.language_model.layers.12.mlp.shared_expert.gate_proj",
"model.language_model.layers.12.mlp.shared_expert.up_proj",
"model.language_model.layers.12.mlp_hyper_connection.block_inject_weight",
"model.language_model.layers.12.mlp_hyper_connection.input_mix_weight_down",
"model.language_model.layers.12.mlp_hyper_connection.input_mix_weight_up",
"model.language_model.layers.13.attn_hyper_connection.block_inject_weight",
"model.language_model.layers.13.attn_hyper_connection.input_mix_weight_down",
"model.language_model.layers.13.attn_hyper_connection.input_mix_weight_up",
"model.language_model.layers.13.linear_attn.in_proj_qkv",
"model.language_model.layers.13.linear_attn.in_proj_z",
"model.language_model.layers.13.linear_attn.out_proj",
"model.language_model.layers.13.mlp.shared_expert.down_proj",
"model.language_model.layers.13.mlp.shared_expert.gate_proj",
"model.language_model.layers.13.mlp.shared_expert.up_proj",
"model.language_model.layers.13.mlp_hyper_connection.block_inject_weight",
"model.language_model.layers.13.mlp_hyper_connection.input_mix_weight_down",
"model.language_model.layers.13.mlp_hyper_connection.input_mix_weight_up",
"model.language_model.layers.14.attn_hyper_connection.block_inject_weight",
"model.language_model.layers.14.attn_hyper_connection.input_mix_weight_down",
"model.language_model.layers.14.attn_hyper_connection.input_mix_weight_up",
"model.language_model.layers.14.linear_attn.in_proj_qkv",
"model.language_model.layers.14.linear_attn.in_proj_z",
"model.language_model.layers.14.linear_attn.out_proj",
"model.language_model.layers.14.mlp.shared_expert.down_proj",
"model.language_model.layers.14.mlp.shared_expert.gate_proj",
"model.language_model.layers.14.mlp.shared_expert.up_proj",
"model.language_model.layers.14.mlp_hyper_connection.block_inject_weight",
"model.language_model.layers.14.mlp_hyper_connection.input_mix_weight_down",
"model.language_model.layers.14.mlp_hyper_connection.input_mix_weight_up",
"model.language_model.layers.15.attn_hyper_connection.block_inject_weight",
"model.language_model.layers.15.attn_hyper_connection.input_mix_weight_down",
"model.language_model.layers.15.attn_hyper_connection.input_mix_weight_up",
"model.language_model.layers.15.mlp.shared_expert.down_proj",
"model.language_model.layers.15.mlp.shared_expert.gate_proj",
"model.language_model.layers.15.mlp.shared_expert.up_proj",
"model.language_model.layers.15.mlp_hyper_connection.block_inject_weight",
"model.language_model.layers.15.mlp_hyper_connection.input_mix_weight_down",
"model.language_model.layers.15.mlp_hyper_connection.input_mix_weight_up",
"model.language_model.layers.15.self_attn.o_proj",
"model.language_model.layers.16.attn_hyper_connection.block_inject_weight",
"model.language_model.layers.16.attn_hyper_connection.input_mix_weight_down",
"model.language_model.layers.16.attn_hyper_connection.input_mix_weight_up",
"model.language_model.layers.16.linear_attn.in_proj_qkv",
"model.language_model.layers.16.linear_attn.in_proj_z",
"model.language_model.layers.16.linear_attn.out_proj",
"model.language_model.layers.16.mlp.shared_expert.down_proj",
"model.language_model.layers.16.mlp.shared_expert.gate_proj",
"model.language_model.layers.16.mlp.shared_expert.up_proj",
"model.language_model.layers.16.mlp_hyper_connection.block_inject_weight",
"model.language_model.layers.16.mlp_hyper_connection.input_mix_weight_down",
"model.language_model.layers.16.mlp_hyper_connection.input_mix_weight_up",
"model.language_model.layers.17.attn_hyper_connection.block_inject_weight",
"model.language_model.layers.17.attn_hyper_connection.input_mix_weight_down",
"model.language_model.layers.17.attn_hyper_connection.input_mix_weight_up",
"model.language_model.layers.17.linear_attn.in_proj_qkv",
"model.language_model.layers.17.linear_attn.in_proj_z",
"model.language_model.layers.17.linear_attn.out_proj",
"model.language_model.layers.17.mlp.shared_expert.down_proj",
"model.language_model.layers.17.mlp.shared_expert.gate_proj",
"model.language_model.layers.17.mlp.shared_expert.up_proj",
"model.language_model.layers.17.mlp_hyper_connection.block_inject_weight",
"model.language_model.layers.17.mlp_hyper_connection.input_mix_weight_down",
"model.language_model.layers.17.mlp_hyper_connection.input_mix_weight_up",
"model.language_model.layers.18.attn_hyper_connection.block_inject_weight",
"model.language_model.layers.18.attn_hyper_connection.input_mix_weight_down",
"model.language_model.layers.18.attn_hyper_connection.input_mix_weight_up",
"model.language_model.layers.18.linear_attn.in_proj_qkv",
"model.language_model.layers.18.linear_attn.in_proj_z",
"model.language_model.layers.18.linear_attn.out_proj",
"model.language_model.layers.18.mlp.shared_expert.down_proj",
"model.language_model.layers.18.mlp.shared_expert.gate_proj",
"model.language_model.layers.18.mlp.shared_expert.up_proj",
"model.language_model.layers.18.mlp_hyper_connection.block_inject_weight",
"model.language_model.layers.18.mlp_hyper_connection.input_mix_weight_down",
"model.language_model.layers.18.mlp_hyper_connection.input_mix_weight_up",
"model.language_model.layers.19.attn_hyper_connection.block_inject_weight",
"model.language_model.layers.19.attn_hyper_connection.input_mix_weight_down",
"model.language_model.layers.19.attn_hyper_connection.input_mix_weight_up",
"model.language_model.layers.19.mlp.shared_expert.down_proj",
"model.language_model.layers.19.mlp.shared_expert.gate_proj",
"model.language_model.layers.19.mlp.shared_expert.up_proj",
"model.language_model.layers.19.mlp_hyper_connection.block_inject_weight",
"model.language_model.layers.19.mlp_hyper_connection.input_mix_weight_down",
"model.language_model.layers.19.mlp_hyper_connection.input_mix_weight_up",
"model.language_model.layers.19.self_attn.o_proj",
"model.language_model.layers.2.attn_hyper_connection.block_inject_weight",
"model.language_model.layers.2.attn_hyper_connection.input_mix_weight_down",
"model.language_model.layers.2.attn_hyper_connection.input_mix_weight_up",
"model.language_model.layers.2.linear_attn.in_proj_qkv",
"model.language_model.layers.2.linear_attn.in_proj_z",
"model.language_model.layers.2.linear_attn.out_proj",
"model.language_model.layers.2.mlp.shared_expert.down_proj",
"model.language_model.layers.2.mlp.shared_expert.gate_proj",
"model.language_model.layers.2.mlp.shared_expert.up_proj",
"model.language_model.layers.2.mlp_hyper_connection.block_inject_weight",
"model.language_model.layers.2.mlp_hyper_connection.input_mix_weight_down",
"model.language_model.layers.2.mlp_hyper_connection.input_mix_weight_up",
"model.language_model.layers.20.attn_hyper_connection.block_inject_weight",
"model.language_model.layers.20.attn_hyper_connection.input_mix_weight_down",
"model.language_model.layers.20.attn_hyper_connection.input_mix_weight_up",
"model.language_model.layers.20.linear_attn.in_proj_qkv",
"model.language_model.layers.20.linear_attn.in_proj_z",
"model.language_model.layers.20.linear_attn.out_proj",
"model.language_model.layers.20.mlp.shared_expert.down_proj",
"model.language_model.layers.20.mlp.shared_expert.gate_proj",
"model.language_model.layers.20.mlp.shared_expert.up_proj",
"model.language_model.layers.20.mlp_hyper_connection.block_inject_weight",
"model.language_model.layers.20.mlp_hyper_connection.input_mix_weight_down",
"model.language_model.layers.20.mlp_hyper_connection.input_mix_weight_up",
"model.language_model.layers.21.attn_hyper_connection.block_inject_weight",
"model.language_model.layers.21.attn_hyper_connection.input_mix_weight_down",
"model.language_model.layers.21.attn_hyper_connection.input_mix_weight_up",
"model.language_model.layers.21.linear_attn.in_proj_qkv",
"model.language_model.layers.21.linear_attn.in_proj_z",
"model.language_model.layers.21.linear_attn.out_proj",
"model.language_model.layers.21.mlp.shared_expert.down_proj",
"model.language_model.layers.21.mlp.shared_expert.gate_proj",
"model.language_model.layers.21.mlp.shared_expert.up_proj",
"model.language_model.layers.21.mlp_hyper_connection.block_inject_weight",
"model.language_model.layers.21.mlp_hyper_connection.input_mix_weight_down",
"model.language_model.layers.21.mlp_hyper_connection.input_mix_weight_up",
"model.language_model.layers.22.attn_hyper_connection.block_inject_weight",
"model.language_model.layers.22.attn_hyper_connection.input_mix_weight_down",
"model.language_model.layers.22.attn_hyper_connection.input_mix_weight_up",
"model.language_model.layers.22.linear_attn.in_proj_qkv",
"model.language_model.layers.22.linear_attn.in_proj_z",
"model.language_model.layers.22.linear_attn.out_proj",
"model.language_model.layers.22.mlp.shared_expert.down_proj",
"model.language_model.layers.22.mlp.shared_expert.gate_proj",
"model.language_model.layers.22.mlp.shared_expert.up_proj",
"model.language_model.layers.22.mlp_hyper_connection.block_inject_weight",
"model.language_model.layers.22.mlp_hyper_connection.input_mix_weight_down",
"model.language_model.layers.22.mlp_hyper_connection.input_mix_weight_up",
"model.language_model.layers.23.attn_hyper_connection.block_inject_weight",
"model.language_model.layers.23.attn_hyper_connection.input_mix_weight_down",
"model.language_model.layers.23.attn_hyper_connection.input_mix_weight_up",
"model.language_model.layers.23.mlp.shared_expert.down_proj",
"model.language_model.layers.23.mlp.shared_expert.gate_proj",
"model.language_model.layers.23.mlp.shared_expert.up_proj",
"model.language_model.layers.23.mlp_hyper_connection.block_inject_weight",
"model.language_model.layers.23.mlp_hyper_connection.input_mix_weight_down",
"model.language_model.layers.23.mlp_hyper_connection.input_mix_weight_up",
"model.language_model.layers.23.self_attn.o_proj",
"model.language_model.layers.24.attn_hyper_connection.block_inject_weight",
"model.language_model.layers.24.attn_hyper_connection.input_mix_weight_down",
"model.language_model.layers.24.attn_hyper_connection.input_mix_weight_up",
"model.language_model.layers.24.linear_attn.in_proj_qkv",
"model.language_model.layers.24.linear_attn.in_proj_z",
"model.language_model.layers.24.linear_attn.out_proj",
"model.language_model.layers.24.mlp.shared_expert.down_proj",
"model.language_model.layers.24.mlp.shared_expert.gate_proj",
"model.language_model.layers.24.mlp.shared_expert.up_proj",
"model.language_model.layers.24.mlp_hyper_connection.block_inject_weight",
"model.language_model.layers.24.mlp_hyper_connection.input_mix_weight_down",
"model.language_model.layers.24.mlp_hyper_connection.input_mix_weight_up",
"model.language_model.layers.25.attn_hyper_connection.block_inject_weight",
"model.language_model.layers.25.attn_hyper_connection.input_mix_weight_down",
"model.language_model.layers.25.attn_hyper_connection.input_mix_weight_up",
"model.language_model.layers.25.linear_attn.in_proj_qkv",
"model.language_model.layers.25.linear_attn.in_proj_z",
"model.language_model.layers.25.linear_attn.out_proj",
"model.language_model.layers.25.mlp.shared_expert.down_proj",
"model.language_model.layers.25.mlp.shared_expert.gate_proj",
"model.language_model.layers.25.mlp.shared_expert.up_proj",
"model.language_model.layers.25.mlp_hyper_connection.block_inject_weight",
"model.language_model.layers.25.mlp_hyper_connection.input_mix_weight_down",
"model.language_model.layers.25.mlp_hyper_connection.input_mix_weight_up",
"model.language_model.layers.26.attn_hyper_connection.block_inject_weight",
"model.language_model.layers.26.attn_hyper_connection.input_mix_weight_down",
"model.language_model.layers.26.attn_hyper_connection.input_mix_weight_up",
"model.language_model.layers.26.linear_attn.in_proj_qkv",
"model.language_model.layers.26.linear_attn.in_proj_z",
"model.language_model.layers.26.linear_attn.out_proj",
"model.language_model.layers.26.mlp.shared_expert.down_proj",
"model.language_model.layers.26.mlp.shared_expert.gate_proj",
"model.language_model.layers.26.mlp.shared_expert.up_proj",
"model.language_model.layers.26.mlp_hyper_connection.block_inject_weight",
"model.language_model.layers.26.mlp_hyper_connection.input_mix_weight_down",
"model.language_model.layers.26.mlp_hyper_connection.input_mix_weight_up",
"model.language_model.layers.27.attn_hyper_connection.block_inject_weight",
"model.language_model.layers.27.attn_hyper_connection.input_mix_weight_down",
"model.language_model.layers.27.attn_hyper_connection.input_mix_weight_up",
"model.language_model.layers.27.mlp.shared_expert.down_proj",
"model.language_model.layers.27.mlp.shared_expert.gate_proj",
"model.language_model.layers.27.mlp.shared_expert.up_proj",
"model.language_model.layers.27.mlp_hyper_connection.block_inject_weight",
"model.language_model.layers.27.mlp_hyper_connection.input_mix_weight_down",
"model.language_model.layers.27.mlp_hyper_connection.input_mix_weight_up",
"model.language_model.layers.27.self_attn.o_proj",
"model.language_model.layers.28.attn_hyper_connection.block_inject_weight",
"model.language_model.layers.28.attn_hyper_connection.input_mix_weight_down",
"model.language_model.layers.28.attn_hyper_connection.input_mix_weight_up",
"model.language_model.layers.28.linear_attn.in_proj_qkv",
"model.language_model.layers.28.linear_attn.in_proj_z",
"model.language_model.layers.28.linear_attn.out_proj",
"model.language_model.layers.28.mlp.shared_expert.down_proj",
"model.language_model.layers.28.mlp.shared_expert.gate_proj",
"model.language_model.layers.28.mlp.shared_expert.up_proj",
"model.language_model.layers.28.mlp_hyper_connection.block_inject_weight",
"model.language_model.layers.28.mlp_hyper_connection.input_mix_weight_down",
"model.language_model.layers.28.mlp_hyper_connection.input_mix_weight_up",
"model.language_model.layers.29.attn_hyper_connection.block_inject_weight",
"model.language_model.layers.29.attn_hyper_connection.input_mix_weight_down",
"model.language_model.layers.29.attn_hyper_connection.input_mix_weight_up",
"model.language_model.layers.29.linear_attn.in_proj_qkv",
"model.language_model.layers.29.linear_attn.in_proj_z",
"model.language_model.layers.29.linear_attn.out_proj",
"model.language_model.layers.29.mlp.shared_expert.down_proj",
"model.language_model.layers.29.mlp.shared_expert.gate_proj",
"model.language_model.layers.29.mlp.shared_expert.up_proj",
"model.language_model.layers.29.mlp_hyper_connection.block_inject_weight",
"model.language_model.layers.29.mlp_hyper_connection.input_mix_weight_down",
"model.language_model.layers.29.mlp_hyper_connection.input_mix_weight_up",
"model.language_model.layers.3.attn_hyper_connection.block_inject_weight",
"model.language_model.layers.3.attn_hyper_connection.input_mix_weight_down",
"model.language_model.layers.3.attn_hyper_connection.input_mix_weight_up",
"model.language_model.layers.3.mlp.shared_expert.down_proj",
"model.language_model.layers.3.mlp.shared_expert.gate_proj",
"model.language_model.layers.3.mlp.shared_expert.up_proj",
"model.language_model.layers.3.mlp_hyper_connection.block_inject_weight",
"model.language_model.layers.3.mlp_hyper_connection.input_mix_weight_down",
"model.language_model.layers.3.mlp_hyper_connection.input_mix_weight_up",
"model.language_model.layers.3.self_attn.o_proj",
"model.language_model.layers.30.attn_hyper_connection.block_inject_weight",
"model.language_model.layers.30.attn_hyper_connection.input_mix_weight_down",
"model.language_model.layers.30.attn_hyper_connection.input_mix_weight_up",
"model.language_model.layers.30.linear_attn.in_proj_qkv",
"model.language_model.layers.30.linear_attn.in_proj_z",
"model.language_model.layers.30.linear_attn.out_proj",
"model.language_model.layers.30.mlp.shared_expert.down_proj",
"model.language_model.layers.30.mlp.shared_expert.gate_proj",
"model.language_model.layers.30.mlp.shared_expert.up_proj",
"model.language_model.layers.30.mlp_hyper_connection.block_inject_weight",
"model.language_model.layers.30.mlp_hyper_connection.input_mix_weight_down",
"model.language_model.layers.30.mlp_hyper_connection.input_mix_weight_up",
"model.language_model.layers.31.attn_hyper_connection.block_inject_weight",
"model.language_model.layers.31.attn_hyper_connection.input_mix_weight_down",
"model.language_model.layers.31.attn_hyper_connection.input_mix_weight_up",
"model.language_model.layers.31.mlp.shared_expert.down_proj",
"model.language_model.layers.31.mlp.shared_expert.gate_proj",
"model.language_model.layers.31.mlp.shared_expert.up_proj",
"model.language_model.layers.31.mlp_hyper_connection.block_inject_weight",
"model.language_model.layers.31.mlp_hyper_connection.input_mix_weight_down",
"model.language_model.layers.31.mlp_hyper_connection.input_mix_weight_up",
"model.language_model.layers.31.self_attn.o_proj",
"model.language_model.layers.32.attn_hyper_connection.block_inject_weight",
"model.language_model.layers.32.attn_hyper_connection.input_mix_weight_down",
"model.language_model.layers.32.attn_hyper_connection.input_mix_weight_up",
"model.language_model.layers.32.linear_attn.in_proj_qkv",
"model.language_model.layers.32.linear_attn.in_proj_z",
"model.language_model.layers.32.linear_attn.out_proj",
"model.language_model.layers.32.mlp.shared_expert.down_proj",
"model.language_model.layers.32.mlp.shared_expert.gate_proj",
"model.language_model.layers.32.mlp.shared_expert.up_proj",
"model.language_model.layers.32.mlp_hyper_connection.block_inject_weight",
"model.language_model.layers.32.mlp_hyper_connection.input_mix_weight_down",
"model.language_model.layers.32.mlp_hyper_connection.input_mix_weight_up",
"model.language_model.layers.33.attn_hyper_connection.block_inject_weight",
"model.language_model.layers.33.attn_hyper_connection.input_mix_weight_down",
"model.language_model.layers.33.attn_hyper_connection.input_mix_weight_up",
"model.language_model.layers.33.linear_attn.in_proj_qkv",
"model.language_model.layers.33.linear_attn.in_proj_z",
"model.language_model.layers.33.linear_attn.out_proj",
"model.language_model.layers.33.mlp.shared_expert.down_proj",
"model.language_model.layers.33.mlp.shared_expert.gate_proj",
"model.language_model.layers.33.mlp.shared_expert.up_proj",
"model.language_model.layers.33.mlp_hyper_connection.block_inject_weight",
"model.language_model.layers.33.mlp_hyper_connection.input_mix_weight_down",
"model.language_model.layers.33.mlp_hyper_connection.input_mix_weight_up",
"model.language_model.layers.34.attn_hyper_connection.block_inject_weight",
"model.language_model.layers.34.attn_hyper_connection.input_mix_weight_down",
"model.language_model.layers.34.attn_hyper_connection.input_mix_weight_up",
"model.language_model.layers.34.linear_attn.in_proj_qkv",
"model.language_model.layers.34.linear_attn.in_proj_z",
"model.language_model.layers.34.linear_attn.out_proj",
"model.language_model.layers.34.mlp.shared_expert.down_proj",
"model.language_model.layers.34.mlp.shared_expert.gate_proj",
"model.language_model.layers.34.mlp.shared_expert.up_proj",
"model.language_model.layers.34.mlp_hyper_connection.block_inject_weight",
"model.language_model.layers.34.mlp_hyper_connection.input_mix_weight_down",
"model.language_model.layers.34.mlp_hyper_connection.input_mix_weight_up",
"model.language_model.layers.35.attn_hyper_connection.block_inject_weight",
"model.language_model.layers.35.attn_hyper_connection.input_mix_weight_down",
"model.language_model.layers.35.attn_hyper_connection.input_mix_weight_up",
"model.language_model.layers.35.mlp.shared_expert.down_proj",
"model.language_model.layers.35.mlp.shared_expert.gate_proj",
"model.language_model.layers.35.mlp.shared_expert.up_proj",
"model.language_model.layers.35.mlp_hyper_connection.block_inject_weight",
"model.language_model.layers.35.mlp_hyper_connection.input_mix_weight_down",
"model.language_model.layers.35.mlp_hyper_connection.input_mix_weight_up",
"model.language_model.layers.35.self_attn.o_proj",
"model.language_model.layers.36.attn_hyper_connection.block_inject_weight",
"model.language_model.layers.36.attn_hyper_connection.input_mix_weight_down",
"model.language_model.layers.36.attn_hyper_connection.input_mix_weight_up",
"model.language_model.layers.36.linear_attn.in_proj_qkv",
"model.language_model.layers.36.linear_attn.in_proj_z",
"model.language_model.layers.36.linear_attn.out_proj",
"model.language_model.layers.36.mlp.shared_expert.down_proj",
"model.language_model.layers.36.mlp.shared_expert.gate_proj",
"model.language_model.layers.36.mlp.shared_expert.up_proj",
"model.language_model.layers.36.mlp_hyper_connection.block_inject_weight",
"model.language_model.layers.36.mlp_hyper_connection.input_mix_weight_down",
"model.language_model.layers.36.mlp_hyper_connection.input_mix_weight_up",
"model.language_model.layers.37.attn_hyper_connection.block_inject_weight",
"model.language_model.layers.37.attn_hyper_connection.input_mix_weight_down",
"model.language_model.layers.37.attn_hyper_connection.input_mix_weight_up",
"model.language_model.layers.37.linear_attn.in_proj_qkv",
"model.language_model.layers.37.linear_attn.in_proj_z",
"model.language_model.layers.37.linear_attn.out_proj",
"model.language_model.layers.37.mlp.shared_expert.down_proj",
"model.language_model.layers.37.mlp.shared_expert.gate_proj",
"model.language_model.layers.37.mlp.shared_expert.up_proj",
"model.language_model.layers.37.mlp_hyper_connection.block_inject_weight",
"model.language_model.layers.37.mlp_hyper_connection.input_mix_weight_down",
"model.language_model.layers.37.mlp_hyper_connection.input_mix_weight_up",
"model.language_model.layers.38.attn_hyper_connection.block_inject_weight",
"model.language_model.layers.38.attn_hyper_connection.input_mix_weight_down",
"model.language_model.layers.38.attn_hyper_connection.input_mix_weight_up",
"model.language_model.layers.38.linear_attn.in_proj_qkv",
"model.language_model.layers.38.linear_attn.in_proj_z",
"model.language_model.layers.38.linear_attn.out_proj",
"model.language_model.layers.38.mlp.shared_expert.down_proj",
"model.language_model.layers.38.mlp.shared_expert.gate_proj",
"model.language_model.layers.38.mlp.shared_expert.up_proj",
"model.language_model.layers.38.mlp_hyper_connection.block_inject_weight",
"model.language_model.layers.38.mlp_hyper_connection.input_mix_weight_down",
"model.language_model.layers.38.mlp_hyper_connection.input_mix_weight_up",
"model.language_model.layers.39.attn_hyper_connection.block_inject_weight",
"model.language_model.layers.39.attn_hyper_connection.input_mix_weight_down",
"model.language_model.layers.39.attn_hyper_connection.input_mix_weight_up",
"model.language_model.layers.39.mlp.shared_expert.down_proj",
"model.language_model.layers.39.mlp.shared_expert.gate_proj",
"model.language_model.layers.39.mlp.shared_expert.up_proj",
"model.language_model.layers.39.mlp_hyper_connection.block_inject_weight",
"model.language_model.layers.39.mlp_hyper_connection.input_mix_weight_down",
"model.language_model.layers.39.mlp_hyper_connection.input_mix_weight_up",
"model.language_model.layers.39.self_attn.o_proj",
"model.language_model.layers.4.attn_hyper_connection.block_inject_weight",
"model.language_model.layers.4.attn_hyper_connection.input_mix_weight_down",
"model.language_model.layers.4.attn_hyper_connection.input_mix_weight_up",
"model.language_model.layers.4.linear_attn.in_proj_qkv",
"model.language_model.layers.4.linear_attn.in_proj_z",
"model.language_model.layers.4.linear_attn.out_proj",
"model.language_model.layers.4.mlp.shared_expert.down_proj",
"model.language_model.layers.4.mlp.shared_expert.gate_proj",
"model.language_model.layers.4.mlp.shared_expert.up_proj",
"model.language_model.layers.4.mlp_hyper_connection.block_inject_weight",
"model.language_model.layers.4.mlp_hyper_connection.input_mix_weight_down",
"model.language_model.layers.4.mlp_hyper_connection.input_mix_weight_up",
"model.language_model.layers.40.attn_hyper_connection.block_inject_weight",
"model.language_model.layers.40.attn_hyper_connection.input_mix_weight_down",
"model.language_model.layers.40.attn_hyper_connection.input_mix_weight_up",
"model.language_model.layers.40.linear_attn.in_proj_qkv",
"model.language_model.layers.40.linear_attn.in_proj_z",
"model.language_model.layers.40.linear_attn.out_proj",
"model.language_model.layers.40.mlp.shared_expert.down_proj",
"model.language_model.layers.40.mlp.shared_expert.gate_proj",
"model.language_model.layers.40.mlp.shared_expert.up_proj",
"model.language_model.layers.40.mlp_hyper_connection.block_inject_weight",
"model.language_model.layers.40.mlp_hyper_connection.input_mix_weight_down",
"model.language_model.layers.40.mlp_hyper_connection.input_mix_weight_up",
"model.language_model.layers.41.attn_hyper_connection.block_inject_weight",
"model.language_model.layers.41.attn_hyper_connection.input_mix_weight_down",
"model.language_model.layers.41.attn_hyper_connection.input_mix_weight_up",
"model.language_model.layers.41.linear_attn.in_proj_qkv",
"model.language_model.layers.41.linear_attn.in_proj_z",
"model.language_model.layers.41.linear_attn.out_proj",
"model.language_model.layers.41.mlp.shared_expert.down_proj",
"model.language_model.layers.41.mlp.shared_expert.gate_proj",
"model.language_model.layers.41.mlp.shared_expert.up_proj",
"model.language_model.layers.41.mlp_hyper_connection.block_inject_weight",
"model.language_model.layers.41.mlp_hyper_connection.input_mix_weight_down",
"model.language_model.layers.41.mlp_hyper_connection.input_mix_weight_up",
"model.language_model.layers.42.attn_hyper_connection.block_inject_weight",
"model.language_model.layers.42.attn_hyper_connection.input_mix_weight_down",
"model.language_model.layers.42.attn_hyper_connection.input_mix_weight_up",
"model.language_model.layers.42.linear_attn.in_proj_qkv",
"model.language_model.layers.42.linear_attn.in_proj_z",
"model.language_model.layers.42.linear_attn.out_proj",
"model.language_model.layers.42.mlp.shared_expert.down_proj",
"model.language_model.layers.42.mlp.shared_expert.gate_proj",
"model.language_model.layers.42.mlp.shared_expert.up_proj",
"model.language_model.layers.42.mlp_hyper_connection.block_inject_weight",
"model.language_model.layers.42.mlp_hyper_connection.input_mix_weight_down",
"model.language_model.layers.42.mlp_hyper_connection.input_mix_weight_up",
"model.language_model.layers.43.attn_hyper_connection.block_inject_weight",
"model.language_model.layers.43.attn_hyper_connection.input_mix_weight_down",
"model.language_model.layers.43.attn_hyper_connection.input_mix_weight_up",
"model.language_model.layers.43.mlp.shared_expert.down_proj",
"model.language_model.layers.43.mlp.shared_expert.gate_proj",
"model.language_model.layers.43.mlp.shared_expert.up_proj",
"model.language_model.layers.43.mlp_hyper_connection.block_inject_weight",
"model.language_model.layers.43.mlp_hyper_connection.input_mix_weight_down",
"model.language_model.layers.43.mlp_hyper_connection.input_mix_weight_up",
"model.language_model.layers.43.self_attn.o_proj",
"model.language_model.layers.44.attn_hyper_connection.block_inject_weight",
"model.language_model.layers.44.attn_hyper_connection.input_mix_weight_down",
"model.language_model.layers.44.attn_hyper_connection.input_mix_weight_up",
"model.language_model.layers.44.linear_attn.in_proj_qkv",
"model.language_model.layers.44.linear_attn.in_proj_z",
"model.language_model.layers.44.linear_attn.out_proj",
"model.language_model.layers.44.mlp.shared_expert.down_proj",
"model.language_model.layers.44.mlp.shared_expert.gate_proj",
"model.language_model.layers.44.mlp.shared_expert.up_proj",
"model.language_model.layers.44.mlp_hyper_connection.block_inject_weight",
"model.language_model.layers.44.mlp_hyper_connection.input_mix_weight_down",
"model.language_model.layers.44.mlp_hyper_connection.input_mix_weight_up",
"model.language_model.layers.45.attn_hyper_connection.block_inject_weight",
"model.language_model.layers.45.attn_hyper_connection.input_mix_weight_down",
"model.language_model.layers.45.attn_hyper_connection.input_mix_weight_up",
"model.language_model.layers.45.linear_attn.in_proj_qkv",
"model.language_model.layers.45.linear_attn.in_proj_z",
"model.language_model.layers.45.linear_attn.out_proj",
"model.language_model.layers.45.mlp.shared_expert.down_proj",
"model.language_model.layers.45.mlp.shared_expert.gate_proj",
"model.language_model.layers.45.mlp.shared_expert.up_proj",
"model.language_model.layers.45.mlp_hyper_connection.block_inject_weight",
"model.language_model.layers.45.mlp_hyper_connection.input_mix_weight_down",
"model.language_model.layers.45.mlp_hyper_connection.input_mix_weight_up",
"model.language_model.layers.46.attn_hyper_connection.block_inject_weight",
"model.language_model.layers.46.attn_hyper_connection.input_mix_weight_down",
"model.language_model.layers.46.attn_hyper_connection.input_mix_weight_up",
"model.language_model.layers.46.linear_attn.in_proj_qkv",
"model.language_model.layers.46.linear_attn.in_proj_z",
"model.language_model.layers.46.linear_attn.out_proj",
"model.language_model.layers.46.mlp.shared_expert.down_proj",
"model.language_model.layers.46.mlp.shared_expert.gate_proj",
"model.language_model.layers.46.mlp.shared_expert.up_proj",
"model.language_model.layers.46.mlp_hyper_connection.block_inject_weight",
"model.language_model.layers.46.mlp_hyper_connection.input_mix_weight_down",
"model.language_model.layers.46.mlp_hyper_connection.input_mix_weight_up",
"model.language_model.layers.47.attn_hyper_connection.block_inject_weight",
"model.language_model.layers.47.attn_hyper_connection.input_mix_weight_down",
"model.language_model.layers.47.attn_hyper_connection.input_mix_weight_up",
"model.language_model.layers.47.mlp.shared_expert.down_proj",
"model.language_model.layers.47.mlp.shared_expert.gate_proj",
"model.language_model.layers.47.mlp.shared_expert.up_proj",
"model.language_model.layers.47.mlp_hyper_connection.block_inject_weight",
"model.language_model.layers.47.mlp_hyper_connection.input_mix_weight_down",
"model.language_model.layers.47.mlp_hyper_connection.input_mix_weight_up",
"model.language_model.layers.47.self_attn.o_proj",
"model.language_model.layers.5.attn_hyper_connection.block_inject_weight",
"model.language_model.layers.5.attn_hyper_connection.input_mix_weight_down",
"model.language_model.layers.5.attn_hyper_connection.input_mix_weight_up",
"model.language_model.layers.5.linear_attn.in_proj_qkv",
"model.language_model.layers.5.linear_attn.in_proj_z",
"model.language_model.layers.5.linear_attn.out_proj",
"model.language_model.layers.5.mlp.shared_expert.down_proj",
"model.language_model.layers.5.mlp.shared_expert.gate_proj",
"model.language_model.layers.5.mlp.shared_expert.up_proj",
"model.language_model.layers.5.mlp_hyper_connection.block_inject_weight",
"model.language_model.layers.5.mlp_hyper_connection.input_mix_weight_down",
"model.language_model.layers.5.mlp_hyper_connection.input_mix_weight_up",
"model.language_model.layers.6.attn_hyper_connection.block_inject_weight",
"model.language_model.layers.6.attn_hyper_connection.input_mix_weight_down",
"model.language_model.layers.6.attn_hyper_connection.input_mix_weight_up",
"model.language_model.layers.6.linear_attn.in_proj_qkv",
"model.language_model.layers.6.linear_attn.in_proj_z",
"model.language_model.layers.6.linear_attn.out_proj",
"model.language_model.layers.6.mlp.shared_expert.down_proj",
"model.language_model.layers.6.mlp.shared_expert.gate_proj",
"model.language_model.layers.6.mlp.shared_expert.up_proj",
"model.language_model.layers.6.mlp_hyper_connection.block_inject_weight",
"model.language_model.layers.6.mlp_hyper_connection.input_mix_weight_down",
"model.language_model.layers.6.mlp_hyper_connection.input_mix_weight_up",
"model.language_model.layers.7.attn_hyper_connection.block_inject_weight",
"model.language_model.layers.7.attn_hyper_connection.input_mix_weight_down",
"model.language_model.layers.7.attn_hyper_connection.input_mix_weight_up",
"model.language_model.layers.7.mlp.shared_expert.down_proj",
"model.language_model.layers.7.mlp.shared_expert.gate_proj",
"model.language_model.layers.7.mlp.shared_expert.up_proj",
"model.language_model.layers.7.mlp_hyper_connection.block_inject_weight",
"model.language_model.layers.7.mlp_hyper_connection.input_mix_weight_down",
"model.language_model.layers.7.mlp_hyper_connection.input_mix_weight_up",
"model.language_model.layers.7.self_attn.o_proj",
"model.language_model.layers.8.attn_hyper_connection.block_inject_weight",
"model.language_model.layers.8.attn_hyper_connection.input_mix_weight_down",
"model.language_model.layers.8.attn_hyper_connection.input_mix_weight_up",
"model.language_model.layers.8.linear_attn.in_proj_qkv",
"model.language_model.layers.8.linear_attn.in_proj_z",
"model.language_model.layers.8.linear_attn.out_proj",
"model.language_model.layers.8.mlp.shared_expert.down_proj",
"model.language_model.layers.8.mlp.shared_expert.gate_proj",
"model.language_model.layers.8.mlp.shared_expert.up_proj",
"model.language_model.layers.8.mlp_hyper_connection.block_inject_weight",
"model.language_model.layers.8.mlp_hyper_connection.input_mix_weight_down",
"model.language_model.layers.8.mlp_hyper_connection.input_mix_weight_up",
"model.language_model.layers.9.attn_hyper_connection.block_inject_weight",
"model.language_model.layers.9.attn_hyper_connection.input_mix_weight_down",
"model.language_model.layers.9.attn_hyper_connection.input_mix_weight_up",
"model.language_model.layers.9.linear_attn.in_proj_qkv",
"model.language_model.layers.9.linear_attn.in_proj_z",
"model.language_model.layers.9.linear_attn.out_proj",
"model.language_model.layers.9.mlp.shared_expert.down_proj",
"model.language_model.layers.9.mlp.shared_expert.gate_proj",
"model.language_model.layers.9.mlp.shared_expert.up_proj",
"model.language_model.layers.9.mlp_hyper_connection.block_inject_weight",
"model.language_model.layers.9.mlp_hyper_connection.input_mix_weight_down",
"model.language_model.layers.9.mlp_hyper_connection.input_mix_weight_up"
]
},
"group_1": {
"weights": {
"dynamic": false,
"num_bits": 4,
"type": "float",
"group_size": 16
},
"targets": [
"model.language_model.layers.0.mlp.experts",
"model.language_model.layers.1.mlp.experts",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_0",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_1",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_10",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_100",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_101",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_102",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_103",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_104",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_105",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_106",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_107",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_108",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_109",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_11",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_110",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_111",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_112",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_113",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_114",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_115",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_116",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_117",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_118",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_119",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_12",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_120",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_121",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_122",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_123",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_124",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_125",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_126",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_127",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_13",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_14",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_15",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_16",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_17",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_18",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_19",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_2",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_20",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_21",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_22",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_23",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_24",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_25",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_26",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_27",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_28",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_29",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_3",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_30",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_31",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_32",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_33",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_34",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_35",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_36",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_37",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_38",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_39",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_4",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_40",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_41",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_42",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_43",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_44",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_45",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_46",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_47",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_48",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_49",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_5",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_50",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_51",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_52",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_53",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_54",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_55",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_56",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_57",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_58",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_59",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_6",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_60",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_61",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_62",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_63",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_64",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_65",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_66",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_67",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_68",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_69",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_7",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_70",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_71",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_72",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_73",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_74",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_75",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_76",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_77",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_78",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_79",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_8",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_80",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_81",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_82",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_83",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_84",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_85",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_86",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_87",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_88",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_89",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_9",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_90",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_91",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_92",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_93",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_94",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_95",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_96",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_97",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_98",
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_99",
"model.language_model.layers.10.mlp.experts",
"model.language_model.layers.11.mlp.experts",
"model.language_model.layers.12.mlp.experts",
"model.language_model.layers.13.mlp.experts",
"model.language_model.layers.14.mlp.experts",
"model.language_model.layers.15.mlp.experts",
"model.language_model.layers.16.mlp.experts",
"model.language_model.layers.17.mlp.experts",
"model.language_model.layers.18.mlp.experts",
"model.language_model.layers.19.mlp.experts",
"model.language_model.layers.2.mlp.experts",
"model.language_model.layers.20.mlp.experts",
"model.language_model.layers.21.mlp.experts",
"model.language_model.layers.22.mlp.experts",
"model.language_model.layers.23.mlp.experts",
"model.language_model.layers.24.mlp.experts",
"model.language_model.layers.25.mlp.experts",
"model.language_model.layers.26.mlp.experts",
"model.language_model.layers.27.mlp.experts",
"model.language_model.layers.28.mlp.experts",
"model.language_model.layers.29.mlp.experts",
"model.language_model.layers.3.mlp.experts",
"model.language_model.layers.30.mlp.experts",
"model.language_model.layers.31.mlp.experts",
"model.language_model.layers.32.mlp.experts",
"model.language_model.layers.33.mlp.experts",
"model.language_model.layers.34.mlp.experts",
"model.language_model.layers.35.mlp.experts",
"model.language_model.layers.36.mlp.experts",
"model.language_model.layers.37.mlp.experts",
"model.language_model.layers.38.mlp.experts",
"model.language_model.layers.39.mlp.experts",
"model.language_model.layers.4.mlp.experts",
"model.language_model.layers.40.mlp.experts",
"model.language_model.layers.41.mlp.experts",
"model.language_model.layers.42.mlp.experts",
"model.language_model.layers.43.mlp.experts",
"model.language_model.layers.44.mlp.experts",
"model.language_model.layers.45.mlp.experts",
"model.language_model.layers.46.mlp.experts",
"model.language_model.layers.47.mlp.experts",
"model.language_model.layers.5.mlp.experts",
"model.language_model.layers.6.mlp.experts",
"model.language_model.layers.7.mlp.experts",
"model.language_model.layers.8.mlp.experts",
"model.language_model.layers.9.mlp.experts",
"mtp.layers.0.mlp.experts"
]
}
},
"quantized_layers": {
"model.language_model.embed_tokens": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.0.linear_attn.out_proj": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.0.linear_attn.in_proj_qkv": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.0.linear_attn.in_proj_z": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.0.mlp.experts": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.0.mlp.shared_expert.gate_proj": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.0.mlp.shared_expert.up_proj": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.0.mlp.shared_expert.down_proj": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.0.attn_hyper_connection.input_mix_weight_down": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.0.attn_hyper_connection.input_mix_weight_up": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.0.attn_hyper_connection.block_inject_weight": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.0.mlp_hyper_connection.input_mix_weight_down": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.0.mlp_hyper_connection.input_mix_weight_up": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.0.mlp_hyper_connection.block_inject_weight": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.1.linear_attn.out_proj": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.1.linear_attn.in_proj_qkv": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.1.linear_attn.in_proj_z": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.1.mlp.experts": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.mlp.shared_expert.gate_proj": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.1.mlp.shared_expert.up_proj": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.1.mlp.shared_expert.down_proj": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_0": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_1": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_2": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_3": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_4": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_5": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_6": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_7": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_8": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_9": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_10": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_11": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_12": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_13": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_14": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_15": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_16": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_17": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_18": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_19": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_20": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_21": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_22": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_23": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_24": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_25": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_26": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_27": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_28": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_29": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_30": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_31": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_32": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_33": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_34": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_35": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_36": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_37": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_38": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_39": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_40": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_41": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_42": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_43": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_44": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_45": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_46": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_47": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_48": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_49": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_50": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_51": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_52": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_53": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_54": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_55": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_56": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_57": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_58": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_59": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_60": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_61": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_62": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_63": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_64": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_65": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_66": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_67": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_68": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_69": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_70": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_71": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_72": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_73": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_74": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_75": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_76": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_77": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_78": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_79": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_80": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_81": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_82": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_83": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_84": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_85": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_86": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_87": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_88": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_89": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_90": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_91": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_92": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_93": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_94": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_95": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_96": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_97": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_98": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_99": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_100": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_101": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_102": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_103": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_104": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_105": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_106": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_107": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_108": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_109": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_110": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_111": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_112": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_113": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_114": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_115": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_116": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_117": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_118": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_119": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_120": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_121": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_122": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_123": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_124": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_125": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_126": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_127": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.ple.key_proj": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.1.ple.value_proj": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.1.attn_hyper_connection.input_mix_weight_down": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.1.attn_hyper_connection.input_mix_weight_up": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.1.attn_hyper_connection.block_inject_weight": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.1.mlp_hyper_connection.input_mix_weight_down": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.1.mlp_hyper_connection.input_mix_weight_up": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.1.mlp_hyper_connection.block_inject_weight": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.2.linear_attn.out_proj": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.2.linear_attn.in_proj_qkv": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.2.linear_attn.in_proj_z": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.2.mlp.experts": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.2.mlp.shared_expert.gate_proj": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.2.mlp.shared_expert.up_proj": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.2.mlp.shared_expert.down_proj": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.2.attn_hyper_connection.input_mix_weight_down": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.2.attn_hyper_connection.input_mix_weight_up": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.2.attn_hyper_connection.block_inject_weight": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.2.mlp_hyper_connection.input_mix_weight_down": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.2.mlp_hyper_connection.input_mix_weight_up": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.2.mlp_hyper_connection.block_inject_weight": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.3.self_attn.o_proj": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.3.mlp.experts": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.3.mlp.shared_expert.gate_proj": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.3.mlp.shared_expert.up_proj": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.3.mlp.shared_expert.down_proj": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.3.attn_hyper_connection.input_mix_weight_down": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.3.attn_hyper_connection.input_mix_weight_up": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.3.attn_hyper_connection.block_inject_weight": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.3.mlp_hyper_connection.input_mix_weight_down": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.3.mlp_hyper_connection.input_mix_weight_up": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.3.mlp_hyper_connection.block_inject_weight": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.4.linear_attn.out_proj": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.4.linear_attn.in_proj_qkv": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.4.linear_attn.in_proj_z": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.4.mlp.experts": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.4.mlp.shared_expert.gate_proj": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.4.mlp.shared_expert.up_proj": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.4.mlp.shared_expert.down_proj": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.4.attn_hyper_connection.input_mix_weight_down": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.4.attn_hyper_connection.input_mix_weight_up": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.4.attn_hyper_connection.block_inject_weight": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.4.mlp_hyper_connection.input_mix_weight_down": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.4.mlp_hyper_connection.input_mix_weight_up": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.4.mlp_hyper_connection.block_inject_weight": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.5.linear_attn.out_proj": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.5.linear_attn.in_proj_qkv": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.5.linear_attn.in_proj_z": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.5.mlp.experts": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.5.mlp.shared_expert.gate_proj": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.5.mlp.shared_expert.up_proj": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.5.mlp.shared_expert.down_proj": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.5.attn_hyper_connection.input_mix_weight_down": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.5.attn_hyper_connection.input_mix_weight_up": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.5.attn_hyper_connection.block_inject_weight": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.5.mlp_hyper_connection.input_mix_weight_down": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.5.mlp_hyper_connection.input_mix_weight_up": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.5.mlp_hyper_connection.block_inject_weight": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.6.linear_attn.out_proj": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.6.linear_attn.in_proj_qkv": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.6.linear_attn.in_proj_z": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.6.mlp.experts": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.6.mlp.shared_expert.gate_proj": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.6.mlp.shared_expert.up_proj": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.6.mlp.shared_expert.down_proj": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.6.attn_hyper_connection.input_mix_weight_down": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.6.attn_hyper_connection.input_mix_weight_up": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.6.attn_hyper_connection.block_inject_weight": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.6.mlp_hyper_connection.input_mix_weight_down": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.6.mlp_hyper_connection.input_mix_weight_up": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.6.mlp_hyper_connection.block_inject_weight": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.7.self_attn.o_proj": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.7.mlp.experts": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.7.mlp.shared_expert.gate_proj": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.7.mlp.shared_expert.up_proj": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.7.mlp.shared_expert.down_proj": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.7.attn_hyper_connection.input_mix_weight_down": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.7.attn_hyper_connection.input_mix_weight_up": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.7.attn_hyper_connection.block_inject_weight": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.7.mlp_hyper_connection.input_mix_weight_down": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.7.mlp_hyper_connection.input_mix_weight_up": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.7.mlp_hyper_connection.block_inject_weight": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.8.linear_attn.out_proj": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.8.linear_attn.in_proj_qkv": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.8.linear_attn.in_proj_z": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.8.mlp.experts": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.8.mlp.shared_expert.gate_proj": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.8.mlp.shared_expert.up_proj": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.8.mlp.shared_expert.down_proj": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.8.attn_hyper_connection.input_mix_weight_down": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.8.attn_hyper_connection.input_mix_weight_up": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.8.attn_hyper_connection.block_inject_weight": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.8.mlp_hyper_connection.input_mix_weight_down": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.8.mlp_hyper_connection.input_mix_weight_up": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.8.mlp_hyper_connection.block_inject_weight": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.9.linear_attn.out_proj": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.9.linear_attn.in_proj_qkv": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.9.linear_attn.in_proj_z": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.9.mlp.experts": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.9.mlp.shared_expert.gate_proj": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.9.mlp.shared_expert.up_proj": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.9.mlp.shared_expert.down_proj": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.9.attn_hyper_connection.input_mix_weight_down": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.9.attn_hyper_connection.input_mix_weight_up": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.9.attn_hyper_connection.block_inject_weight": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.9.mlp_hyper_connection.input_mix_weight_down": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.9.mlp_hyper_connection.input_mix_weight_up": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.9.mlp_hyper_connection.block_inject_weight": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.10.linear_attn.out_proj": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.10.linear_attn.in_proj_qkv": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.10.linear_attn.in_proj_z": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.10.mlp.experts": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.10.mlp.shared_expert.gate_proj": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.10.mlp.shared_expert.up_proj": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.10.mlp.shared_expert.down_proj": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.10.attn_hyper_connection.input_mix_weight_down": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.10.attn_hyper_connection.input_mix_weight_up": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.10.attn_hyper_connection.block_inject_weight": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.10.mlp_hyper_connection.input_mix_weight_down": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.10.mlp_hyper_connection.input_mix_weight_up": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.10.mlp_hyper_connection.block_inject_weight": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.11.self_attn.o_proj": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.11.mlp.experts": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.11.mlp.shared_expert.gate_proj": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.11.mlp.shared_expert.up_proj": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.11.mlp.shared_expert.down_proj": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.11.attn_hyper_connection.input_mix_weight_down": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.11.attn_hyper_connection.input_mix_weight_up": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.11.attn_hyper_connection.block_inject_weight": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.11.mlp_hyper_connection.input_mix_weight_down": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.