codelion's picture
Add files using upload-large-folder tool
c7972e3 verified
Raw
History Blame Contribute Delete
61.3 kB
{
"architectures": [
"LLaDA2MoeModelLM"
],
"attention_dropout": 0.0,
"auto_map": {
"AutoConfig": "configuration_llada2_moe.LLaDA2MoeConfig",
"AutoModel": "modeling_llada2_moe.LLaDA2MoeModel",
"AutoModelForCausalLM": "modeling_llada2_moe.LLaDA2MoeModelLM"
},
"block_size": 32,
"embedding_dropout": 0.0,
"eos_token_id": [
156892,
156900
],
"expert_capacity": 48,
"first_k_dense_replace": 1,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 9216,
"max_position_embeddings": 131072,
"max_window_layers": 28,
"model_type": "llada2_moe",
"moe_intermediate_size": 1024,
"moe_router_enable_expert_bias": true,
"n_group": 8,
"norm_head": false,
"norm_softmax": false,
"norm_topk_prob": true,
"num_attention_heads": 32,
"num_experts": 256,
"num_experts_per_tok": 8,
"num_hidden_layers": 32,
"num_key_value_heads": 4,
"num_shared_experts": 1,
"output_dropout": 0.0,
"output_router_logits": false,
"pad_token_id": 156892,
"partial_rotary_factor": 0.5,
"quantization": {
"group_size": 64,
"bits": 4,
"mode": "affine",
"model.word_embeddings": {
"bits": 4,
"group_size": 64
},
"model.layers.0.attention.query_key_value": {
"bits": 4,
"group_size": 64
},
"model.layers.0.attention.dense": {
"bits": 4,
"group_size": 64
},
"model.layers.0.mlp.gate_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.0.mlp.up_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.0.mlp.down_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.1.attention.query_key_value": {
"bits": 4,
"group_size": 64
},
"model.layers.1.attention.dense": {
"bits": 4,
"group_size": 64
},
"model.layers.1.mlp.switch_mlp.gate_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.1.mlp.switch_mlp.up_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.1.mlp.switch_mlp.down_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.1.mlp.shared_experts.gate_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.1.mlp.shared_experts.up_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.1.mlp.shared_experts.down_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.2.attention.query_key_value": {
"bits": 4,
"group_size": 64
},
"model.layers.2.attention.dense": {
"bits": 4,
"group_size": 64
},
"model.layers.2.mlp.switch_mlp.gate_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.2.mlp.switch_mlp.up_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.2.mlp.switch_mlp.down_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.2.mlp.shared_experts.gate_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.2.mlp.shared_experts.up_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.2.mlp.shared_experts.down_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.3.attention.query_key_value": {
"bits": 4,
"group_size": 64
},
"model.layers.3.attention.dense": {
"bits": 4,
"group_size": 64
},
"model.layers.3.mlp.switch_mlp.gate_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.3.mlp.switch_mlp.up_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.3.mlp.switch_mlp.down_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.3.mlp.shared_experts.gate_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.3.mlp.shared_experts.up_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.3.mlp.shared_experts.down_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.4.attention.query_key_value": {
"bits": 4,
"group_size": 64
},
"model.layers.4.attention.dense": {
"bits": 4,
"group_size": 64
},
"model.layers.4.mlp.switch_mlp.gate_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.4.mlp.switch_mlp.up_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.4.mlp.switch_mlp.down_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.4.mlp.shared_experts.gate_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.4.mlp.shared_experts.up_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.4.mlp.shared_experts.down_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.5.attention.query_key_value": {
"bits": 4,
"group_size": 64
},
"model.layers.5.attention.dense": {
"bits": 4,
"group_size": 64
},
"model.layers.5.mlp.switch_mlp.gate_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.5.mlp.switch_mlp.up_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.5.mlp.switch_mlp.down_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.5.mlp.shared_experts.gate_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.5.mlp.shared_experts.up_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.5.mlp.shared_experts.down_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.6.attention.query_key_value": {
"bits": 4,
"group_size": 64
},
"model.layers.6.attention.dense": {
"bits": 4,
"group_size": 64
},
"model.layers.6.mlp.switch_mlp.gate_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.6.mlp.switch_mlp.up_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.6.mlp.switch_mlp.down_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.6.mlp.shared_experts.gate_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.6.mlp.shared_experts.up_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.6.mlp.shared_experts.down_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.7.attention.query_key_value": {
"bits": 4,
"group_size": 64
},
"model.layers.7.attention.dense": {
"bits": 4,
"group_size": 64
},
"model.layers.7.mlp.switch_mlp.gate_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.7.mlp.switch_mlp.up_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.7.mlp.switch_mlp.down_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.7.mlp.shared_experts.gate_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.7.mlp.shared_experts.up_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.7.mlp.shared_experts.down_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.8.attention.query_key_value": {
"bits": 4,
"group_size": 64
},
"model.layers.8.attention.dense": {
"bits": 4,
"group_size": 64
},
"model.layers.8.mlp.switch_mlp.gate_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.8.mlp.switch_mlp.up_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.8.mlp.switch_mlp.down_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.8.mlp.shared_experts.gate_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.8.mlp.shared_experts.up_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.8.mlp.shared_experts.down_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.9.attention.query_key_value": {
"bits": 4,
"group_size": 64
},
"model.layers.9.attention.dense": {
"bits": 4,
"group_size": 64
},
"model.layers.9.mlp.switch_mlp.gate_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.9.mlp.switch_mlp.up_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.9.mlp.switch_mlp.down_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.9.mlp.shared_experts.gate_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.9.mlp.shared_experts.up_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.9.mlp.shared_experts.down_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.10.attention.query_key_value": {
"bits": 4,
"group_size": 64
},
"model.layers.10.attention.dense": {
"bits": 4,
"group_size": 64
},
"model.layers.10.mlp.switch_mlp.gate_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.10.mlp.switch_mlp.up_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.10.mlp.switch_mlp.down_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.10.mlp.shared_experts.gate_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.10.mlp.shared_experts.up_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.10.mlp.shared_experts.down_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.11.attention.query_key_value": {
"bits": 4,
"group_size": 64
},
"model.layers.11.attention.dense": {
"bits": 4,
"group_size": 64
},
"model.layers.11.mlp.switch_mlp.gate_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.11.mlp.switch_mlp.up_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.11.mlp.switch_mlp.down_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.11.mlp.shared_experts.gate_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.11.mlp.shared_experts.up_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.11.mlp.shared_experts.down_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.12.attention.query_key_value": {
"bits": 4,
"group_size": 64
},
"model.layers.12.attention.dense": {
"bits": 4,
"group_size": 64
},
"model.layers.12.mlp.switch_mlp.gate_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.12.mlp.switch_mlp.up_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.12.mlp.switch_mlp.down_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.12.mlp.shared_experts.gate_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.12.mlp.shared_experts.up_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.12.mlp.shared_experts.down_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.13.attention.query_key_value": {
"bits": 4,
"group_size": 64
},
"model.layers.13.attention.dense": {
"bits": 4,
"group_size": 64
},
"model.layers.13.mlp.switch_mlp.gate_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.13.mlp.switch_mlp.up_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.13.mlp.switch_mlp.down_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.13.mlp.shared_experts.gate_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.13.mlp.shared_experts.up_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.13.mlp.shared_experts.down_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.14.attention.query_key_value": {
"bits": 4,
"group_size": 64
},
"model.layers.14.attention.dense": {
"bits": 4,
"group_size": 64
},
"model.layers.14.mlp.switch_mlp.gate_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.14.mlp.switch_mlp.up_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.14.mlp.switch_mlp.down_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.14.mlp.shared_experts.gate_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.14.mlp.shared_experts.up_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.14.mlp.shared_experts.down_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.15.attention.query_key_value": {
"bits": 4,
"group_size": 64
},
"model.layers.15.attention.dense": {
"bits": 4,
"group_size": 64
},
"model.layers.15.mlp.switch_mlp.gate_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.15.mlp.switch_mlp.up_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.15.mlp.switch_mlp.down_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.15.mlp.shared_experts.gate_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.15.mlp.shared_experts.up_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.15.mlp.shared_experts.down_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.16.attention.query_key_value": {
"bits": 4,
"group_size": 64
},
"model.layers.16.attention.dense": {
"bits": 4,
"group_size": 64
},
"model.layers.16.mlp.switch_mlp.gate_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.16.mlp.switch_mlp.up_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.16.mlp.switch_mlp.down_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.16.mlp.shared_experts.gate_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.16.mlp.shared_experts.up_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.16.mlp.shared_experts.down_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.17.attention.query_key_value": {
"bits": 4,
"group_size": 64
},
"model.layers.17.attention.dense": {
"bits": 4,
"group_size": 64
},
"model.layers.17.mlp.switch_mlp.gate_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.17.mlp.switch_mlp.up_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.17.mlp.switch_mlp.down_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.17.mlp.shared_experts.gate_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.17.mlp.shared_experts.up_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.17.mlp.shared_experts.down_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.18.attention.query_key_value": {
"bits": 4,
"group_size": 64
},
"model.layers.18.attention.dense": {
"bits": 4,
"group_size": 64
},
"model.layers.18.mlp.switch_mlp.gate_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.18.mlp.switch_mlp.up_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.18.mlp.switch_mlp.down_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.18.mlp.shared_experts.gate_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.18.mlp.shared_experts.up_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.18.mlp.shared_experts.down_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.19.attention.query_key_value": {
"bits": 4,
"group_size": 64
},
"model.layers.19.attention.dense": {
"bits": 4,
"group_size": 64
},
"model.layers.19.mlp.switch_mlp.gate_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.19.mlp.switch_mlp.up_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.19.mlp.switch_mlp.down_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.19.mlp.shared_experts.gate_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.19.mlp.shared_experts.up_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.19.mlp.shared_experts.down_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.20.attention.query_key_value": {
"bits": 4,
"group_size": 64
},
"model.layers.20.attention.dense": {
"bits": 4,
"group_size": 64
},
"model.layers.20.mlp.switch_mlp.gate_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.20.mlp.switch_mlp.up_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.20.mlp.switch_mlp.down_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.20.mlp.shared_experts.gate_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.20.mlp.shared_experts.up_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.20.mlp.shared_experts.down_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.21.attention.query_key_value": {
"bits": 4,
"group_size": 64
},
"model.layers.21.attention.dense": {
"bits": 4,
"group_size": 64
},
"model.layers.21.mlp.switch_mlp.gate_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.21.mlp.switch_mlp.up_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.21.mlp.switch_mlp.down_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.21.mlp.shared_experts.gate_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.21.mlp.shared_experts.up_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.21.mlp.shared_experts.down_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.22.attention.query_key_value": {
"bits": 4,
"group_size": 64
},
"model.layers.22.attention.dense": {
"bits": 4,
"group_size": 64
},
"model.layers.22.mlp.switch_mlp.gate_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.22.mlp.switch_mlp.up_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.22.mlp.switch_mlp.down_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.22.mlp.shared_experts.gate_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.22.mlp.shared_experts.up_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.22.mlp.shared_experts.down_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.23.attention.query_key_value": {
"bits": 4,
"group_size": 64
},
"model.layers.23.attention.dense": {
"bits": 4,
"group_size": 64
},
"model.layers.23.mlp.switch_mlp.gate_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.23.mlp.switch_mlp.up_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.23.mlp.switch_mlp.down_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.23.mlp.shared_experts.gate_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.23.mlp.shared_experts.up_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.23.mlp.shared_experts.down_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.24.attention.query_key_value": {
"bits": 4,
"group_size": 64
},
"model.layers.24.attention.dense": {
"bits": 4,
"group_size": 64
},
"model.layers.24.mlp.switch_mlp.gate_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.24.mlp.switch_mlp.up_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.24.mlp.switch_mlp.down_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.24.mlp.shared_experts.gate_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.24.mlp.shared_experts.up_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.24.mlp.shared_experts.down_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.25.attention.query_key_value": {
"bits": 4,
"group_size": 64
},
"model.layers.25.attention.dense": {
"bits": 4,
"group_size": 64
},
"model.layers.25.mlp.switch_mlp.gate_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.25.mlp.switch_mlp.up_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.25.mlp.switch_mlp.down_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.25.mlp.shared_experts.gate_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.25.mlp.shared_experts.up_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.25.mlp.shared_experts.down_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.26.attention.query_key_value": {
"bits": 4,
"group_size": 64
},
"model.layers.26.attention.dense": {
"bits": 4,
"group_size": 64
},
"model.layers.26.mlp.switch_mlp.gate_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.26.mlp.switch_mlp.up_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.26.mlp.switch_mlp.down_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.26.mlp.shared_experts.gate_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.26.mlp.shared_experts.up_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.26.mlp.shared_experts.down_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.27.attention.query_key_value": {
"bits": 4,
"group_size": 64
},
"model.layers.27.attention.dense": {
"bits": 4,
"group_size": 64
},
"model.layers.27.mlp.switch_mlp.gate_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.27.mlp.switch_mlp.up_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.27.mlp.switch_mlp.down_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.27.mlp.shared_experts.gate_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.27.mlp.shared_experts.up_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.27.mlp.shared_experts.down_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.28.attention.query_key_value": {
"bits": 4,
"group_size": 64
},
"model.layers.28.attention.dense": {
"bits": 4,
"group_size": 64
},
"model.layers.28.mlp.switch_mlp.gate_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.28.mlp.switch_mlp.up_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.28.mlp.switch_mlp.down_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.28.mlp.shared_experts.gate_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.28.mlp.shared_experts.up_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.28.mlp.shared_experts.down_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.29.attention.query_key_value": {
"bits": 4,
"group_size": 64
},
"model.layers.29.attention.dense": {
"bits": 4,
"group_size": 64
},
"model.layers.29.mlp.switch_mlp.gate_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.29.mlp.switch_mlp.up_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.29.mlp.switch_mlp.down_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.29.mlp.shared_experts.gate_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.29.mlp.shared_experts.up_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.29.mlp.shared_experts.down_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.30.attention.query_key_value": {
"bits": 4,
"group_size": 64
},
"model.layers.30.attention.dense": {
"bits": 4,
"group_size": 64
},
"model.layers.30.mlp.switch_mlp.gate_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.30.mlp.switch_mlp.up_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.30.mlp.switch_mlp.down_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.30.mlp.shared_experts.gate_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.30.mlp.shared_experts.up_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.30.mlp.shared_experts.down_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.31.attention.query_key_value": {
"bits": 4,
"group_size": 64
},
"model.layers.31.attention.dense": {
"bits": 4,
"group_size": 64
},
"model.layers.31.mlp.switch_mlp.gate_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.31.mlp.switch_mlp.up_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.31.mlp.switch_mlp.down_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.31.mlp.shared_experts.gate_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.31.mlp.shared_experts.up_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.31.mlp.shared_experts.down_proj": {
"bits": 4,
"group_size": 64
},
"lm_head": {
"bits": 4,
"group_size": 64
}
},
"quantization_config": {
"group_size": 64,
"bits": 4,
"mode": "affine",
"model.word_embeddings": {
"bits": 4,
"group_size": 64
},
"model.layers.0.attention.query_key_value": {
"bits": 4,
"group_size": 64
},
"model.layers.0.attention.dense": {
"bits": 4,
"group_size": 64
},
"model.layers.0.mlp.gate_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.0.mlp.up_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.0.mlp.down_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.1.attention.query_key_value": {
"bits": 4,
"group_size": 64
},
"model.layers.1.attention.dense": {
"bits": 4,
"group_size": 64
},
"model.layers.1.mlp.switch_mlp.gate_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.1.mlp.switch_mlp.up_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.1.mlp.switch_mlp.down_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.1.mlp.shared_experts.gate_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.1.mlp.shared_experts.up_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.1.mlp.shared_experts.down_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.2.attention.query_key_value": {
"bits": 4,
"group_size": 64
},
"model.layers.2.attention.dense": {
"bits": 4,
"group_size": 64
},
"model.layers.2.mlp.switch_mlp.gate_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.2.mlp.switch_mlp.up_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.2.mlp.switch_mlp.down_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.2.mlp.shared_experts.gate_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.2.mlp.shared_experts.up_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.2.mlp.shared_experts.down_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.3.attention.query_key_value": {
"bits": 4,
"group_size": 64
},
"model.layers.3.attention.dense": {
"bits": 4,
"group_size": 64
},
"model.layers.3.mlp.switch_mlp.gate_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.3.mlp.switch_mlp.up_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.3.mlp.switch_mlp.down_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.3.mlp.shared_experts.gate_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.3.mlp.shared_experts.up_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.3.mlp.shared_experts.down_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.4.attention.query_key_value": {
"bits": 4,
"group_size": 64
},
"model.layers.4.attention.dense": {
"bits": 4,
"group_size": 64
},
"model.layers.4.mlp.switch_mlp.gate_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.4.mlp.switch_mlp.up_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.4.mlp.switch_mlp.down_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.4.mlp.shared_experts.gate_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.4.mlp.shared_experts.up_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.4.mlp.shared_experts.down_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.5.attention.query_key_value": {
"bits": 4,
"group_size": 64
},
"model.layers.5.attention.dense": {
"bits": 4,
"group_size": 64
},
"model.layers.5.mlp.switch_mlp.gate_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.5.mlp.switch_mlp.up_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.5.mlp.switch_mlp.down_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.5.mlp.shared_experts.gate_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.5.mlp.shared_experts.up_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.5.mlp.shared_experts.down_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.6.attention.query_key_value": {
"bits": 4,
"group_size": 64
},
"model.layers.6.attention.dense": {
"bits": 4,
"group_size": 64
},
"model.layers.6.mlp.switch_mlp.gate_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.6.mlp.switch_mlp.up_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.6.mlp.switch_mlp.down_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.6.mlp.shared_experts.gate_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.6.mlp.shared_experts.up_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.6.mlp.shared_experts.down_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.7.attention.query_key_value": {
"bits": 4,
"group_size": 64
},
"model.layers.7.attention.dense": {
"bits": 4,
"group_size": 64
},
"model.layers.7.mlp.switch_mlp.gate_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.7.mlp.switch_mlp.up_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.7.mlp.switch_mlp.down_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.7.mlp.shared_experts.gate_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.7.mlp.shared_experts.up_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.7.mlp.shared_experts.down_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.8.attention.query_key_value": {
"bits": 4,
"group_size": 64
},
"model.layers.8.attention.dense": {
"bits": 4,
"group_size": 64
},
"model.layers.8.mlp.switch_mlp.gate_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.8.mlp.switch_mlp.up_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.8.mlp.switch_mlp.down_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.8.mlp.shared_experts.gate_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.8.mlp.shared_experts.up_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.8.mlp.shared_experts.down_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.9.attention.query_key_value": {
"bits": 4,
"group_size": 64
},
"model.layers.9.attention.dense": {
"bits": 4,
"group_size": 64
},
"model.layers.9.mlp.switch_mlp.gate_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.9.mlp.switch_mlp.up_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.9.mlp.switch_mlp.down_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.9.mlp.shared_experts.gate_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.9.mlp.shared_experts.up_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.9.mlp.shared_experts.down_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.10.attention.query_key_value": {
"bits": 4,
"group_size": 64
},
"model.layers.10.attention.dense": {
"bits": 4,
"group_size": 64
},
"model.layers.10.mlp.switch_mlp.gate_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.10.mlp.switch_mlp.up_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.10.mlp.switch_mlp.down_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.10.mlp.shared_experts.gate_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.10.mlp.shared_experts.up_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.10.mlp.shared_experts.down_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.11.attention.query_key_value": {
"bits": 4,
"group_size": 64
},
"model.layers.11.attention.dense": {
"bits": 4,
"group_size": 64
},
"model.layers.11.mlp.switch_mlp.gate_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.11.mlp.switch_mlp.up_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.11.mlp.switch_mlp.down_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.11.mlp.shared_experts.gate_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.11.mlp.shared_experts.up_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.11.mlp.shared_experts.down_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.12.attention.query_key_value": {
"bits": 4,
"group_size": 64
},
"model.layers.12.attention.dense": {
"bits": 4,
"group_size": 64
},
"model.layers.12.mlp.switch_mlp.gate_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.12.mlp.switch_mlp.up_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.12.mlp.switch_mlp.down_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.12.mlp.shared_experts.gate_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.12.mlp.shared_experts.up_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.12.mlp.shared_experts.down_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.13.attention.query_key_value": {
"bits": 4,
"group_size": 64
},
"model.layers.13.attention.dense": {
"bits": 4,
"group_size": 64
},
"model.layers.13.mlp.switch_mlp.gate_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.13.mlp.switch_mlp.up_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.13.mlp.switch_mlp.down_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.13.mlp.shared_experts.gate_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.13.mlp.shared_experts.up_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.13.mlp.shared_experts.down_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.14.attention.query_key_value": {
"bits": 4,
"group_size": 64
},
"model.layers.14.attention.dense": {
"bits": 4,
"group_size": 64
},
"model.layers.14.mlp.switch_mlp.gate_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.14.mlp.switch_mlp.up_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.14.mlp.switch_mlp.down_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.14.mlp.shared_experts.gate_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.14.mlp.shared_experts.up_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.14.mlp.shared_experts.down_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.15.attention.query_key_value": {
"bits": 4,
"group_size": 64
},
"model.layers.15.attention.dense": {
"bits": 4,
"group_size": 64
},
"model.layers.15.mlp.switch_mlp.gate_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.15.mlp.switch_mlp.up_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.15.mlp.switch_mlp.down_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.15.mlp.shared_experts.gate_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.15.mlp.shared_experts.up_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.15.mlp.shared_experts.down_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.16.attention.query_key_value": {
"bits": 4,
"group_size": 64
},
"model.layers.16.attention.dense": {
"bits": 4,
"group_size": 64
},
"model.layers.16.mlp.switch_mlp.gate_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.16.mlp.switch_mlp.up_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.16.mlp.switch_mlp.down_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.16.mlp.shared_experts.gate_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.16.mlp.shared_experts.up_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.16.mlp.shared_experts.down_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.17.attention.query_key_value": {
"bits": 4,
"group_size": 64
},
"model.layers.17.attention.dense": {
"bits": 4,
"group_size": 64
},
"model.layers.17.mlp.switch_mlp.gate_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.17.mlp.switch_mlp.up_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.17.mlp.switch_mlp.down_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.17.mlp.shared_experts.gate_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.17.mlp.shared_experts.up_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.17.mlp.shared_experts.down_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.18.attention.query_key_value": {
"bits": 4,
"group_size": 64
},
"model.layers.18.attention.dense": {
"bits": 4,
"group_size": 64
},
"model.layers.18.mlp.switch_mlp.gate_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.18.mlp.switch_mlp.up_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.18.mlp.switch_mlp.down_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.18.mlp.shared_experts.gate_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.18.mlp.shared_experts.up_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.18.mlp.shared_experts.down_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.19.attention.query_key_value": {
"bits": 4,
"group_size": 64
},
"model.layers.19.attention.dense": {
"bits": 4,
"group_size": 64
},
"model.layers.19.mlp.switch_mlp.gate_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.19.mlp.switch_mlp.up_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.19.mlp.switch_mlp.down_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.19.mlp.shared_experts.gate_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.19.mlp.shared_experts.up_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.19.mlp.shared_experts.down_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.20.attention.query_key_value": {
"bits": 4,
"group_size": 64
},
"model.layers.20.attention.dense": {
"bits": 4,
"group_size": 64
},
"model.layers.20.mlp.switch_mlp.gate_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.20.mlp.switch_mlp.up_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.20.mlp.switch_mlp.down_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.20.mlp.shared_experts.gate_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.20.mlp.shared_experts.up_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.20.mlp.shared_experts.down_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.21.attention.query_key_value": {
"bits": 4,
"group_size": 64
},
"model.layers.21.attention.dense": {
"bits": 4,
"group_size": 64
},
"model.layers.21.mlp.switch_mlp.gate_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.21.mlp.switch_mlp.up_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.21.mlp.switch_mlp.down_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.21.mlp.shared_experts.gate_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.21.mlp.shared_experts.up_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.21.mlp.shared_experts.down_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.22.attention.query_key_value": {
"bits": 4,
"group_size": 64
},
"model.layers.22.attention.dense": {
"bits": 4,
"group_size": 64
},
"model.layers.22.mlp.switch_mlp.gate_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.22.mlp.switch_mlp.up_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.22.mlp.switch_mlp.down_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.22.mlp.shared_experts.gate_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.22.mlp.shared_experts.up_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.22.mlp.shared_experts.down_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.23.attention.query_key_value": {
"bits": 4,
"group_size": 64
},
"model.layers.23.attention.dense": {
"bits": 4,
"group_size": 64
},
"model.layers.23.mlp.switch_mlp.gate_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.23.mlp.switch_mlp.up_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.23.mlp.switch_mlp.down_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.23.mlp.shared_experts.gate_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.23.mlp.shared_experts.up_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.23.mlp.shared_experts.down_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.24.attention.query_key_value": {
"bits": 4,
"group_size": 64
},
"model.layers.24.attention.dense": {
"bits": 4,
"group_size": 64
},
"model.layers.24.mlp.switch_mlp.gate_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.24.mlp.switch_mlp.up_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.24.mlp.switch_mlp.down_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.24.mlp.shared_experts.gate_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.24.mlp.shared_experts.up_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.24.mlp.shared_experts.down_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.25.attention.query_key_value": {
"bits": 4,
"group_size": 64
},
"model.layers.25.attention.dense": {
"bits": 4,
"group_size": 64
},
"model.layers.25.mlp.switch_mlp.gate_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.25.mlp.switch_mlp.up_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.25.mlp.switch_mlp.down_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.25.mlp.shared_experts.gate_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.25.mlp.shared_experts.up_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.25.mlp.shared_experts.down_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.26.attention.query_key_value": {
"bits": 4,
"group_size": 64
},
"model.layers.26.attention.dense": {
"bits": 4,
"group_size": 64
},
"model.layers.26.mlp.switch_mlp.gate_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.26.mlp.switch_mlp.up_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.26.mlp.switch_mlp.down_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.26.mlp.shared_experts.gate_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.26.mlp.shared_experts.up_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.26.mlp.shared_experts.down_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.27.attention.query_key_value": {
"bits": 4,
"group_size": 64
},
"model.layers.27.attention.dense": {
"bits": 4,
"group_size": 64
},
"model.layers.27.mlp.switch_mlp.gate_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.27.mlp.switch_mlp.up_proj": {
"bits": 2,
"group_size": 64
},
"model.layers.27.mlp.switch_mlp.down_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.27.mlp.shared_experts.gate_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.27.mlp.shared_experts.up_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.27.mlp.shared_experts.down_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.28.attention.query_key_value": {
"bits": 4,
"group_size": 64
},
"model.layers.28.attention.dense": {
"bits": 4,
"group_size": 64
},
"model.layers.28.mlp.switch_mlp.gate_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.28.mlp.switch_mlp.up_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.28.mlp.switch_mlp.down_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.28.mlp.shared_experts.gate_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.28.mlp.shared_experts.up_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.28.mlp.shared_experts.down_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.29.attention.query_key_value": {
"bits": 4,
"group_size": 64
},
"model.layers.29.attention.dense": {
"bits": 4,
"group_size": 64
},
"model.layers.29.mlp.switch_mlp.gate_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.29.mlp.switch_mlp.up_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.29.mlp.switch_mlp.down_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.29.mlp.shared_experts.gate_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.29.mlp.shared_experts.up_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.29.mlp.shared_experts.down_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.30.attention.query_key_value": {
"bits": 4,
"group_size": 64
},
"model.layers.30.attention.dense": {
"bits": 4,
"group_size": 64
},
"model.layers.30.mlp.switch_mlp.gate_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.30.mlp.switch_mlp.up_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.30.mlp.switch_mlp.down_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.30.mlp.shared_experts.gate_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.30.mlp.shared_experts.up_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.30.mlp.shared_experts.down_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.31.attention.query_key_value": {
"bits": 4,
"group_size": 64
},
"model.layers.31.attention.dense": {
"bits": 4,
"group_size": 64
},
"model.layers.31.mlp.switch_mlp.gate_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.31.mlp.switch_mlp.up_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.31.mlp.switch_mlp.down_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.31.mlp.shared_experts.gate_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.31.mlp.shared_experts.up_proj": {
"bits": 4,
"group_size": 64
},
"model.layers.31.mlp.shared_experts.down_proj": {
"bits": 4,
"group_size": 64
},
"lm_head": {
"bits": 4,
"group_size": 64
}
},
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 3000000,
"rotary_dim": 64,
"routed_scaling_factor": 2.5,
"router_dtype": "fp32",
"score_function": "sigmoid",
"tie_word_embeddings": false,
"topk_group": 4,
"torch_dtype": "bfloat16",
"transformers_version": "5.2.0",
"use_bias": false,
"use_cache": false,
"use_qk_norm": true,
"use_qkv_bias": false,
"use_rmsnorm": true,
"use_sliding_window": false,
"using_split_qkv_in_self_attention": false,
"vocab_size": 157184
}