Ovis2-4B-PYTORCH-INT4 / quant_config.json
Azaz666's picture
Upload PyTorch quantized model (pure PyTorch, no custom CUDA kernels)
b3a72ef verified
{
"method": "pytorch_int4",
"quant_bits": 4,
"family": "ovis2",
"model_id": "AIDC-AI/Ovis2-4B",
"n_linear_quantized": 253,
"skip_vision_quant": true,
"int4_layers": {
"llm.model.layers.0.self_attn.q_proj": {
"in_features": 2048,
"out_features": 2048,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.0.self_attn.k_proj": {
"in_features": 2048,
"out_features": 256,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.0.self_attn.v_proj": {
"in_features": 2048,
"out_features": 256,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.0.self_attn.o_proj": {
"in_features": 2048,
"out_features": 2048,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.0.mlp.gate_proj": {
"in_features": 2048,
"out_features": 11008,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.0.mlp.up_proj": {
"in_features": 2048,
"out_features": 11008,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.0.mlp.down_proj": {
"in_features": 11008,
"out_features": 2048,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.1.self_attn.q_proj": {
"in_features": 2048,
"out_features": 2048,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.1.self_attn.k_proj": {
"in_features": 2048,
"out_features": 256,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.1.self_attn.v_proj": {
"in_features": 2048,
"out_features": 256,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.1.self_attn.o_proj": {
"in_features": 2048,
"out_features": 2048,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.1.mlp.gate_proj": {
"in_features": 2048,
"out_features": 11008,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.1.mlp.up_proj": {
"in_features": 2048,
"out_features": 11008,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.1.mlp.down_proj": {
"in_features": 11008,
"out_features": 2048,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.2.self_attn.q_proj": {
"in_features": 2048,
"out_features": 2048,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.2.self_attn.k_proj": {
"in_features": 2048,
"out_features": 256,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.2.self_attn.v_proj": {
"in_features": 2048,
"out_features": 256,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.2.self_attn.o_proj": {
"in_features": 2048,
"out_features": 2048,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.2.mlp.gate_proj": {
"in_features": 2048,
"out_features": 11008,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.2.mlp.up_proj": {
"in_features": 2048,
"out_features": 11008,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.2.mlp.down_proj": {
"in_features": 11008,
"out_features": 2048,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.3.self_attn.q_proj": {
"in_features": 2048,
"out_features": 2048,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.3.self_attn.k_proj": {
"in_features": 2048,
"out_features": 256,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.3.self_attn.v_proj": {
"in_features": 2048,
"out_features": 256,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.3.self_attn.o_proj": {
"in_features": 2048,
"out_features": 2048,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.3.mlp.gate_proj": {
"in_features": 2048,
"out_features": 11008,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.3.mlp.up_proj": {
"in_features": 2048,
"out_features": 11008,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.3.mlp.down_proj": {
"in_features": 11008,
"out_features": 2048,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.4.self_attn.q_proj": {
"in_features": 2048,
"out_features": 2048,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.4.self_attn.k_proj": {
"in_features": 2048,
"out_features": 256,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.4.self_attn.v_proj": {
"in_features": 2048,
"out_features": 256,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.4.self_attn.o_proj": {
"in_features": 2048,
"out_features": 2048,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.4.mlp.gate_proj": {
"in_features": 2048,
"out_features": 11008,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.4.mlp.up_proj": {
"in_features": 2048,
"out_features": 11008,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.4.mlp.down_proj": {
"in_features": 11008,
"out_features": 2048,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.5.self_attn.q_proj": {
"in_features": 2048,
"out_features": 2048,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.5.self_attn.k_proj": {
"in_features": 2048,
"out_features": 256,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.5.self_attn.v_proj": {
"in_features": 2048,
"out_features": 256,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.5.self_attn.o_proj": {
"in_features": 2048,
"out_features": 2048,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.5.mlp.gate_proj": {
"in_features": 2048,
"out_features": 11008,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.5.mlp.up_proj": {
"in_features": 2048,
"out_features": 11008,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.5.mlp.down_proj": {
"in_features": 11008,
"out_features": 2048,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.6.self_attn.q_proj": {
"in_features": 2048,
"out_features": 2048,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.6.self_attn.k_proj": {
"in_features": 2048,
"out_features": 256,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.6.self_attn.v_proj": {
"in_features": 2048,
"out_features": 256,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.6.self_attn.o_proj": {
"in_features": 2048,
"out_features": 2048,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.6.mlp.gate_proj": {
"in_features": 2048,
"out_features": 11008,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.6.mlp.up_proj": {
"in_features": 2048,
"out_features": 11008,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.6.mlp.down_proj": {
"in_features": 11008,
"out_features": 2048,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.7.self_attn.q_proj": {
"in_features": 2048,
"out_features": 2048,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.7.self_attn.k_proj": {
"in_features": 2048,
"out_features": 256,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.7.self_attn.v_proj": {
"in_features": 2048,
"out_features": 256,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.7.self_attn.o_proj": {
"in_features": 2048,
"out_features": 2048,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.7.mlp.gate_proj": {
"in_features": 2048,
"out_features": 11008,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.7.mlp.up_proj": {
"in_features": 2048,
"out_features": 11008,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.7.mlp.down_proj": {
"in_features": 11008,
"out_features": 2048,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.8.self_attn.q_proj": {
"in_features": 2048,
"out_features": 2048,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.8.self_attn.k_proj": {
"in_features": 2048,
"out_features": 256,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.8.self_attn.v_proj": {
"in_features": 2048,
"out_features": 256,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.8.self_attn.o_proj": {
"in_features": 2048,
"out_features": 2048,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.8.mlp.gate_proj": {
"in_features": 2048,
"out_features": 11008,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.8.mlp.up_proj": {
"in_features": 2048,
"out_features": 11008,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.8.mlp.down_proj": {
"in_features": 11008,
"out_features": 2048,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.9.self_attn.q_proj": {
"in_features": 2048,
"out_features": 2048,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.9.self_attn.k_proj": {
"in_features": 2048,
"out_features": 256,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.9.self_attn.v_proj": {
"in_features": 2048,
"out_features": 256,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.9.self_attn.o_proj": {
"in_features": 2048,
"out_features": 2048,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.9.mlp.gate_proj": {
"in_features": 2048,
"out_features": 11008,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.9.mlp.up_proj": {
"in_features": 2048,
"out_features": 11008,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.9.mlp.down_proj": {
"in_features": 11008,
"out_features": 2048,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.10.self_attn.q_proj": {
"in_features": 2048,
"out_features": 2048,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.10.self_attn.k_proj": {
"in_features": 2048,
"out_features": 256,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.10.self_attn.v_proj": {
"in_features": 2048,
"out_features": 256,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.10.self_attn.o_proj": {
"in_features": 2048,
"out_features": 2048,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.10.mlp.gate_proj": {
"in_features": 2048,
"out_features": 11008,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.10.mlp.up_proj": {
"in_features": 2048,
"out_features": 11008,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.10.mlp.down_proj": {
"in_features": 11008,
"out_features": 2048,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.11.self_attn.q_proj": {
"in_features": 2048,
"out_features": 2048,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.11.self_attn.k_proj": {
"in_features": 2048,
"out_features": 256,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.11.self_attn.v_proj": {
"in_features": 2048,
"out_features": 256,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.11.self_attn.o_proj": {
"in_features": 2048,
"out_features": 2048,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.11.mlp.gate_proj": {
"in_features": 2048,
"out_features": 11008,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.11.mlp.up_proj": {
"in_features": 2048,
"out_features": 11008,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.11.mlp.down_proj": {
"in_features": 11008,
"out_features": 2048,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.12.self_attn.q_proj": {
"in_features": 2048,
"out_features": 2048,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.12.self_attn.k_proj": {
"in_features": 2048,
"out_features": 256,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.12.self_attn.v_proj": {
"in_features": 2048,
"out_features": 256,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.12.self_attn.o_proj": {
"in_features": 2048,
"out_features": 2048,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.12.mlp.gate_proj": {
"in_features": 2048,
"out_features": 11008,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.12.mlp.up_proj": {
"in_features": 2048,
"out_features": 11008,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.12.mlp.down_proj": {
"in_features": 11008,
"out_features": 2048,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.13.self_attn.q_proj": {
"in_features": 2048,
"out_features": 2048,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.13.self_attn.k_proj": {
"in_features": 2048,
"out_features": 256,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.13.self_attn.v_proj": {
"in_features": 2048,
"out_features": 256,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.13.self_attn.o_proj": {
"in_features": 2048,
"out_features": 2048,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.13.mlp.gate_proj": {
"in_features": 2048,
"out_features": 11008,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.13.mlp.up_proj": {
"in_features": 2048,
"out_features": 11008,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.13.mlp.down_proj": {
"in_features": 11008,
"out_features": 2048,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.14.self_attn.q_proj": {
"in_features": 2048,
"out_features": 2048,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.14.self_attn.k_proj": {
"in_features": 2048,
"out_features": 256,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.14.self_attn.v_proj": {
"in_features": 2048,
"out_features": 256,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.14.self_attn.o_proj": {
"in_features": 2048,
"out_features": 2048,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.14.mlp.gate_proj": {
"in_features": 2048,
"out_features": 11008,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.14.mlp.up_proj": {
"in_features": 2048,
"out_features": 11008,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.14.mlp.down_proj": {
"in_features": 11008,
"out_features": 2048,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.15.self_attn.q_proj": {
"in_features": 2048,
"out_features": 2048,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.15.self_attn.k_proj": {
"in_features": 2048,
"out_features": 256,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.15.self_attn.v_proj": {
"in_features": 2048,
"out_features": 256,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.15.self_attn.o_proj": {
"in_features": 2048,
"out_features": 2048,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.15.mlp.gate_proj": {
"in_features": 2048,
"out_features": 11008,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.15.mlp.up_proj": {
"in_features": 2048,
"out_features": 11008,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.15.mlp.down_proj": {
"in_features": 11008,
"out_features": 2048,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.16.self_attn.q_proj": {
"in_features": 2048,
"out_features": 2048,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.16.self_attn.k_proj": {
"in_features": 2048,
"out_features": 256,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.16.self_attn.v_proj": {
"in_features": 2048,
"out_features": 256,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.16.self_attn.o_proj": {
"in_features": 2048,
"out_features": 2048,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.16.mlp.gate_proj": {
"in_features": 2048,
"out_features": 11008,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.16.mlp.up_proj": {
"in_features": 2048,
"out_features": 11008,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.16.mlp.down_proj": {
"in_features": 11008,
"out_features": 2048,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.17.self_attn.q_proj": {
"in_features": 2048,
"out_features": 2048,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.17.self_attn.k_proj": {
"in_features": 2048,
"out_features": 256,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.17.self_attn.v_proj": {
"in_features": 2048,
"out_features": 256,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.17.self_attn.o_proj": {
"in_features": 2048,
"out_features": 2048,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.17.mlp.gate_proj": {
"in_features": 2048,
"out_features": 11008,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.17.mlp.up_proj": {
"in_features": 2048,
"out_features": 11008,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.17.mlp.down_proj": {
"in_features": 11008,
"out_features": 2048,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.18.self_attn.q_proj": {
"in_features": 2048,
"out_features": 2048,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.18.self_attn.k_proj": {
"in_features": 2048,
"out_features": 256,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.18.self_attn.v_proj": {
"in_features": 2048,
"out_features": 256,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.18.self_attn.o_proj": {
"in_features": 2048,
"out_features": 2048,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.18.mlp.gate_proj": {
"in_features": 2048,
"out_features": 11008,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.18.mlp.up_proj": {
"in_features": 2048,
"out_features": 11008,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.18.mlp.down_proj": {
"in_features": 11008,
"out_features": 2048,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.19.self_attn.q_proj": {
"in_features": 2048,
"out_features": 2048,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.19.self_attn.k_proj": {
"in_features": 2048,
"out_features": 256,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.19.self_attn.v_proj": {
"in_features": 2048,
"out_features": 256,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.19.self_attn.o_proj": {
"in_features": 2048,
"out_features": 2048,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.19.mlp.gate_proj": {
"in_features": 2048,
"out_features": 11008,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.19.mlp.up_proj": {
"in_features": 2048,
"out_features": 11008,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.19.mlp.down_proj": {
"in_features": 11008,
"out_features": 2048,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.20.self_attn.q_proj": {
"in_features": 2048,
"out_features": 2048,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.20.self_attn.k_proj": {
"in_features": 2048,
"out_features": 256,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.20.self_attn.v_proj": {
"in_features": 2048,
"out_features": 256,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.20.self_attn.o_proj": {
"in_features": 2048,
"out_features": 2048,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.20.mlp.gate_proj": {
"in_features": 2048,
"out_features": 11008,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.20.mlp.up_proj": {
"in_features": 2048,
"out_features": 11008,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.20.mlp.down_proj": {
"in_features": 11008,
"out_features": 2048,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.21.self_attn.q_proj": {
"in_features": 2048,
"out_features": 2048,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.21.self_attn.k_proj": {
"in_features": 2048,
"out_features": 256,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.21.self_attn.v_proj": {
"in_features": 2048,
"out_features": 256,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.21.self_attn.o_proj": {
"in_features": 2048,
"out_features": 2048,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.21.mlp.gate_proj": {
"in_features": 2048,
"out_features": 11008,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.21.mlp.up_proj": {
"in_features": 2048,
"out_features": 11008,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.21.mlp.down_proj": {
"in_features": 11008,
"out_features": 2048,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.22.self_attn.q_proj": {
"in_features": 2048,
"out_features": 2048,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.22.self_attn.k_proj": {
"in_features": 2048,
"out_features": 256,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.22.self_attn.v_proj": {
"in_features": 2048,
"out_features": 256,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.22.self_attn.o_proj": {
"in_features": 2048,
"out_features": 2048,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.22.mlp.gate_proj": {
"in_features": 2048,
"out_features": 11008,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.22.mlp.up_proj": {
"in_features": 2048,
"out_features": 11008,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.22.mlp.down_proj": {
"in_features": 11008,
"out_features": 2048,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.23.self_attn.q_proj": {
"in_features": 2048,
"out_features": 2048,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.23.self_attn.k_proj": {
"in_features": 2048,
"out_features": 256,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.23.self_attn.v_proj": {
"in_features": 2048,
"out_features": 256,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.23.self_attn.o_proj": {
"in_features": 2048,
"out_features": 2048,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.23.mlp.gate_proj": {
"in_features": 2048,
"out_features": 11008,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.23.mlp.up_proj": {
"in_features": 2048,
"out_features": 11008,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.23.mlp.down_proj": {
"in_features": 11008,
"out_features": 2048,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.24.self_attn.q_proj": {
"in_features": 2048,
"out_features": 2048,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.24.self_attn.k_proj": {
"in_features": 2048,
"out_features": 256,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.24.self_attn.v_proj": {
"in_features": 2048,
"out_features": 256,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.24.self_attn.o_proj": {
"in_features": 2048,
"out_features": 2048,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.24.mlp.gate_proj": {
"in_features": 2048,
"out_features": 11008,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.24.mlp.up_proj": {
"in_features": 2048,
"out_features": 11008,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.24.mlp.down_proj": {
"in_features": 11008,
"out_features": 2048,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.25.self_attn.q_proj": {
"in_features": 2048,
"out_features": 2048,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.25.self_attn.k_proj": {
"in_features": 2048,
"out_features": 256,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.25.self_attn.v_proj": {
"in_features": 2048,
"out_features": 256,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.25.self_attn.o_proj": {
"in_features": 2048,
"out_features": 2048,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.25.mlp.gate_proj": {
"in_features": 2048,
"out_features": 11008,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.25.mlp.up_proj": {
"in_features": 2048,
"out_features": 11008,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.25.mlp.down_proj": {
"in_features": 11008,
"out_features": 2048,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.26.self_attn.q_proj": {
"in_features": 2048,
"out_features": 2048,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.26.self_attn.k_proj": {
"in_features": 2048,
"out_features": 256,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.26.self_attn.v_proj": {
"in_features": 2048,
"out_features": 256,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.26.self_attn.o_proj": {
"in_features": 2048,
"out_features": 2048,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.26.mlp.gate_proj": {
"in_features": 2048,
"out_features": 11008,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.26.mlp.up_proj": {
"in_features": 2048,
"out_features": 11008,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.26.mlp.down_proj": {
"in_features": 11008,
"out_features": 2048,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.27.self_attn.q_proj": {
"in_features": 2048,
"out_features": 2048,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.27.self_attn.k_proj": {
"in_features": 2048,
"out_features": 256,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.27.self_attn.v_proj": {
"in_features": 2048,
"out_features": 256,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.27.self_attn.o_proj": {
"in_features": 2048,
"out_features": 2048,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.27.mlp.gate_proj": {
"in_features": 2048,
"out_features": 11008,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.27.mlp.up_proj": {
"in_features": 2048,
"out_features": 11008,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.27.mlp.down_proj": {
"in_features": 11008,
"out_features": 2048,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.28.self_attn.q_proj": {
"in_features": 2048,
"out_features": 2048,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.28.self_attn.k_proj": {
"in_features": 2048,
"out_features": 256,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.28.self_attn.v_proj": {
"in_features": 2048,
"out_features": 256,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.28.self_attn.o_proj": {
"in_features": 2048,
"out_features": 2048,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.28.mlp.gate_proj": {
"in_features": 2048,
"out_features": 11008,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.28.mlp.up_proj": {
"in_features": 2048,
"out_features": 11008,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.28.mlp.down_proj": {
"in_features": 11008,
"out_features": 2048,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.29.self_attn.q_proj": {
"in_features": 2048,
"out_features": 2048,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.29.self_attn.k_proj": {
"in_features": 2048,
"out_features": 256,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.29.self_attn.v_proj": {
"in_features": 2048,
"out_features": 256,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.29.self_attn.o_proj": {
"in_features": 2048,
"out_features": 2048,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.29.mlp.gate_proj": {
"in_features": 2048,
"out_features": 11008,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.29.mlp.up_proj": {
"in_features": 2048,
"out_features": 11008,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.29.mlp.down_proj": {
"in_features": 11008,
"out_features": 2048,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.30.self_attn.q_proj": {
"in_features": 2048,
"out_features": 2048,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.30.self_attn.k_proj": {
"in_features": 2048,
"out_features": 256,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.30.self_attn.v_proj": {
"in_features": 2048,
"out_features": 256,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.30.self_attn.o_proj": {
"in_features": 2048,
"out_features": 2048,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.30.mlp.gate_proj": {
"in_features": 2048,
"out_features": 11008,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.30.mlp.up_proj": {
"in_features": 2048,
"out_features": 11008,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.30.mlp.down_proj": {
"in_features": 11008,
"out_features": 2048,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.31.self_attn.q_proj": {
"in_features": 2048,
"out_features": 2048,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.31.self_attn.k_proj": {
"in_features": 2048,
"out_features": 256,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.31.self_attn.v_proj": {
"in_features": 2048,
"out_features": 256,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.31.self_attn.o_proj": {
"in_features": 2048,
"out_features": 2048,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.31.mlp.gate_proj": {
"in_features": 2048,
"out_features": 11008,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.31.mlp.up_proj": {
"in_features": 2048,
"out_features": 11008,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.31.mlp.down_proj": {
"in_features": 11008,
"out_features": 2048,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.32.self_attn.q_proj": {
"in_features": 2048,
"out_features": 2048,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.32.self_attn.k_proj": {
"in_features": 2048,
"out_features": 256,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.32.self_attn.v_proj": {
"in_features": 2048,
"out_features": 256,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.32.self_attn.o_proj": {
"in_features": 2048,
"out_features": 2048,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.32.mlp.gate_proj": {
"in_features": 2048,
"out_features": 11008,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.32.mlp.up_proj": {
"in_features": 2048,
"out_features": 11008,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.32.mlp.down_proj": {
"in_features": 11008,
"out_features": 2048,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.33.self_attn.q_proj": {
"in_features": 2048,
"out_features": 2048,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.33.self_attn.k_proj": {
"in_features": 2048,
"out_features": 256,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.33.self_attn.v_proj": {
"in_features": 2048,
"out_features": 256,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.33.self_attn.o_proj": {
"in_features": 2048,
"out_features": 2048,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.33.mlp.gate_proj": {
"in_features": 2048,
"out_features": 11008,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.33.mlp.up_proj": {
"in_features": 2048,
"out_features": 11008,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.33.mlp.down_proj": {
"in_features": 11008,
"out_features": 2048,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.34.self_attn.q_proj": {
"in_features": 2048,
"out_features": 2048,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.34.self_attn.k_proj": {
"in_features": 2048,
"out_features": 256,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.34.self_attn.v_proj": {
"in_features": 2048,
"out_features": 256,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.34.self_attn.o_proj": {
"in_features": 2048,
"out_features": 2048,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.34.mlp.gate_proj": {
"in_features": 2048,
"out_features": 11008,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.34.mlp.up_proj": {
"in_features": 2048,
"out_features": 11008,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.34.mlp.down_proj": {
"in_features": 11008,
"out_features": 2048,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.35.self_attn.q_proj": {
"in_features": 2048,
"out_features": 2048,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.35.self_attn.k_proj": {
"in_features": 2048,
"out_features": 256,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.35.self_attn.v_proj": {
"in_features": 2048,
"out_features": 256,
"group_size": 128,
"has_bias": true
},
"llm.model.layers.35.self_attn.o_proj": {
"in_features": 2048,
"out_features": 2048,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.35.mlp.gate_proj": {
"in_features": 2048,
"out_features": 11008,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.35.mlp.up_proj": {
"in_features": 2048,
"out_features": 11008,
"group_size": 128,
"has_bias": false
},
"llm.model.layers.35.mlp.down_proj": {
"in_features": 11008,
"out_features": 2048,
"group_size": 128,
"has_bias": false
},
"llm.lm_head": {
"in_features": 2048,
"out_features": 151936,
"group_size": 128,
"has_bias": false
}
},
"group_size": 128
}