|
{ |
|
"metadata": { |
|
"total_size": 6170393600 |
|
}, |
|
"weight_map": { |
|
"model.embed_tokens.weight": "model-00001-of-00002.safetensors", |
|
"model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"model.layers.0.mlp.down_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.0.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.0.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.0.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.0.mlp.down_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.0.mlp.gate_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.0.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.0.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.0.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.0.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.0.mlp.up_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.0.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.0.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.0.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.0.mlp.up_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"model.layers.0.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"model.layers.0.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.0.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.0.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.0.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.0.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.0.self_attn.o_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.0.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.0.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.0.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.0.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.0.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.0.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.0.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.0.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.0.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.0.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.0.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.0.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"model.layers.1.mlp.down_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.1.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.1.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.1.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.1.mlp.down_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.1.mlp.gate_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.1.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.1.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.1.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.1.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.1.mlp.up_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.1.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.1.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.1.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.1.mlp.up_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"model.layers.1.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"model.layers.1.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.1.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.1.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.1.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.1.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.1.self_attn.o_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.1.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.1.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.1.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.1.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.1.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.1.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.1.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.1.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.1.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.1.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.1.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.1.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"model.layers.10.mlp.down_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.10.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.10.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.10.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.10.mlp.down_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.10.mlp.gate_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.10.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.10.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.10.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.10.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.10.mlp.up_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.10.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.10.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.10.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.10.mlp.up_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"model.layers.10.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"model.layers.10.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.10.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.10.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.10.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.10.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.10.self_attn.o_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.10.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.10.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.10.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.10.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.10.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.10.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.10.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.10.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.10.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.10.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.10.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.10.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"model.layers.11.mlp.down_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.11.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.11.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.11.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.11.mlp.down_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.11.mlp.gate_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.11.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.11.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.11.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.11.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.11.mlp.up_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.11.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.11.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.11.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.11.mlp.up_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"model.layers.11.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"model.layers.11.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.11.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.11.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.11.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.11.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.11.self_attn.o_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.11.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.11.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.11.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.11.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.11.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.11.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.11.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.11.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.11.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.11.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.11.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.11.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"model.layers.12.mlp.down_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.12.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.12.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.12.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.12.mlp.down_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.12.mlp.gate_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.12.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.12.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.12.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.12.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.12.mlp.up_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.12.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.12.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.12.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.12.mlp.up_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"model.layers.12.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"model.layers.12.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.12.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.12.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.12.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.12.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.12.self_attn.o_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.12.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.12.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.12.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.12.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.12.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.12.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.12.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.12.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.12.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.12.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.12.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.12.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"model.layers.13.mlp.down_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.13.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.13.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.13.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.13.mlp.down_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.13.mlp.gate_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.13.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.13.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.13.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.13.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.13.mlp.up_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.13.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.13.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.13.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.13.mlp.up_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"model.layers.13.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"model.layers.13.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.13.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.13.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.13.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.13.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.13.self_attn.o_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.13.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.13.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.13.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.13.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.13.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.13.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.13.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.13.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.13.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.13.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.13.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.13.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"model.layers.14.mlp.down_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.14.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.14.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.14.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.14.mlp.down_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.14.mlp.gate_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.14.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.14.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.14.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.14.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.14.mlp.up_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.14.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.14.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.14.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.14.mlp.up_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"model.layers.14.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"model.layers.14.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.14.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.14.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.14.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.14.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.14.self_attn.o_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.14.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.14.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.14.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.14.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.14.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.14.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.14.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.14.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.14.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.14.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.14.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.14.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"model.layers.15.mlp.down_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.15.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.15.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.15.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.15.mlp.down_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.15.mlp.gate_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.15.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.15.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.15.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.15.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.15.mlp.up_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.15.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.15.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.15.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.15.mlp.up_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"model.layers.15.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"model.layers.15.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.15.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.15.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.15.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.15.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.15.self_attn.o_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.15.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.15.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.15.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.15.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.15.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.15.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.15.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.15.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.15.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.15.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.15.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.15.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"model.layers.16.mlp.down_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.16.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.16.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.16.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.16.mlp.down_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.16.mlp.gate_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.16.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.16.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.16.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.16.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.16.mlp.up_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.16.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.16.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.16.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.16.mlp.up_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"model.layers.16.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"model.layers.16.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.16.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.16.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.16.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.16.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.16.self_attn.o_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.16.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.16.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.16.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.16.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.16.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.16.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.16.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.16.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.16.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.16.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.16.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.16.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"model.layers.17.mlp.down_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.17.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.17.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.17.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.17.mlp.down_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.17.mlp.gate_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.17.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.17.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.17.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.17.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.17.mlp.up_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.17.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.17.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.17.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.17.mlp.up_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"model.layers.17.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"model.layers.17.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.17.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.17.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.17.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.17.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.17.self_attn.o_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.17.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.17.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.17.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.17.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.17.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.17.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.17.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.17.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.17.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.17.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.17.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.17.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"model.layers.18.mlp.down_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.18.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.18.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.18.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.18.mlp.down_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.18.mlp.gate_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.18.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.18.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.18.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.18.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.18.mlp.up_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.18.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.18.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.18.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.18.mlp.up_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"model.layers.18.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"model.layers.18.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.18.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.18.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.18.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.18.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.18.self_attn.o_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.18.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.18.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.18.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.18.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.18.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.18.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.18.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.18.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.18.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.18.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.18.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.18.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"model.layers.19.mlp.down_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.19.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.19.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.19.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.19.mlp.down_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.19.mlp.gate_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.19.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.19.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.19.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.19.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.19.mlp.up_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.19.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.19.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.19.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.19.mlp.up_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"model.layers.19.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"model.layers.19.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.19.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.19.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.19.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.19.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.19.self_attn.o_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.19.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.19.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.19.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.19.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.19.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.19.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.19.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.19.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.19.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.19.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.19.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.19.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"model.layers.2.mlp.down_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.2.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.2.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.2.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.2.mlp.down_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.2.mlp.gate_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.2.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.2.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.2.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.2.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.2.mlp.up_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.2.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.2.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.2.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.2.mlp.up_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"model.layers.2.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"model.layers.2.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.2.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.2.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.2.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.2.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.2.self_attn.o_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.2.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.2.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.2.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.2.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.2.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.2.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.2.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.2.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.2.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.2.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.2.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.2.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"model.layers.20.mlp.down_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.20.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.20.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.20.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.20.mlp.down_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.20.mlp.gate_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.20.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.20.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.20.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.20.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.20.mlp.up_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.20.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.20.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.20.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.20.mlp.up_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"model.layers.20.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"model.layers.20.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.20.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.20.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.20.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.20.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.20.self_attn.o_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.20.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.20.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.20.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.20.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.20.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.20.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.20.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.20.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.20.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.20.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.20.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.20.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"model.layers.21.mlp.down_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.21.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.21.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.21.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.21.mlp.down_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.21.mlp.gate_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.21.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.21.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.21.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.21.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.21.mlp.up_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.21.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.21.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.21.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.21.mlp.up_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"model.layers.21.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"model.layers.21.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.21.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.21.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.21.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.21.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.21.self_attn.o_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.21.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.21.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.21.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.21.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.21.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.21.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.21.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.21.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.21.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.21.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.21.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.21.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"model.layers.22.mlp.down_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.22.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.22.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.22.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.22.mlp.down_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.22.mlp.gate_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.22.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.22.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.22.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.22.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.22.mlp.up_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.22.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.22.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.22.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.22.mlp.up_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"model.layers.22.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"model.layers.22.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"model.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.22.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.22.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.22.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.22.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.22.self_attn.o_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.22.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.22.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.22.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.22.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.22.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.22.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.22.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.22.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.22.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.22.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.22.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.22.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"model.layers.23.mlp.down_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.23.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.23.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.23.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.23.mlp.down_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.23.mlp.gate_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.23.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.23.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.23.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.23.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.23.mlp.up_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.23.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.23.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.23.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.23.mlp.up_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"model.layers.23.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"model.layers.23.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"model.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.23.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.23.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.23.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.23.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.23.self_attn.o_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.23.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.23.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.23.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.23.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.23.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.23.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.23.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.23.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.23.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.23.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.23.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.23.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"model.layers.24.mlp.down_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.24.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.24.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.24.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.24.mlp.down_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.24.mlp.gate_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.24.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.24.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.24.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.24.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.24.mlp.up_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.24.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.24.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.24.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.24.mlp.up_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"model.layers.24.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"model.layers.24.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"model.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.24.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.24.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.24.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.24.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.24.self_attn.o_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.24.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.24.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.24.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.24.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.24.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.24.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.24.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.24.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.24.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.24.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.24.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.24.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"model.layers.25.mlp.down_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.25.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.25.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.25.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.25.mlp.down_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.25.mlp.gate_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.25.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.25.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.25.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.25.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.25.mlp.up_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.25.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.25.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.25.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.25.mlp.up_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"model.layers.25.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"model.layers.25.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"model.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.25.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.25.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.25.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.25.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.25.self_attn.o_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.25.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.25.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.25.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.25.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.25.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.25.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.25.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.25.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.25.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.25.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.25.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.25.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"model.layers.26.mlp.down_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.26.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.26.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.26.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.26.mlp.down_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.26.mlp.gate_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.26.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.26.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.26.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.26.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.26.mlp.up_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.26.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.26.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.26.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.26.mlp.up_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"model.layers.26.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"model.layers.26.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"model.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.26.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.26.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.26.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.26.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.26.self_attn.o_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.26.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.26.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.26.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.26.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.26.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.26.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.26.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.26.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.26.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.26.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.26.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.26.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"model.layers.27.mlp.down_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.27.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.27.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.27.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.27.mlp.down_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.27.mlp.gate_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.27.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.27.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.27.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.27.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.27.mlp.up_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.27.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.27.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.27.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.27.mlp.up_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"model.layers.27.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"model.layers.27.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"model.layers.27.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.27.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.27.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.27.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.27.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.27.self_attn.o_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.27.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.27.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.27.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.27.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.27.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.27.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors", |
|
"model.layers.27.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", |
|
"model.layers.27.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", |
|
"model.layers.27.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", |
|
"model.layers.27.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", |
|
"model.layers.27.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors", |
|