{ "metadata": { "total_size": 1765637120 }, "weight_map": { "model.decoder.embed_positions.weight": "model-00002-of-00004.safetensors", "model.decoder.embed_tokens.weight": "model-00002-of-00004.safetensors", "model.decoder.layer_norm.bias": "model-00004-of-00004.safetensors", "model.decoder.layer_norm.weight": "model-00004-of-00004.safetensors", "model.decoder.layers.0.encoder_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.decoder.layers.0.encoder_attn.out_proj.bias": "model-00003-of-00004.safetensors", "model.decoder.layers.0.encoder_attn.out_proj.weight": "model-00003-of-00004.safetensors", "model.decoder.layers.0.encoder_attn.q_proj.bias": "model-00002-of-00004.safetensors", "model.decoder.layers.0.encoder_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.decoder.layers.0.encoder_attn.v_proj.bias": "model-00002-of-00004.safetensors", "model.decoder.layers.0.encoder_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.decoder.layers.0.encoder_attn_layer_norm.bias": "model-00003-of-00004.safetensors", "model.decoder.layers.0.encoder_attn_layer_norm.weight": "model-00003-of-00004.safetensors", "model.decoder.layers.0.fc1.bias": "model-00003-of-00004.safetensors", "model.decoder.layers.0.fc1.weight": "model-00003-of-00004.safetensors", "model.decoder.layers.0.fc2.bias": "model-00003-of-00004.safetensors", "model.decoder.layers.0.fc2.weight": "model-00003-of-00004.safetensors", "model.decoder.layers.0.final_layer_norm.bias": "model-00003-of-00004.safetensors", "model.decoder.layers.0.final_layer_norm.weight": "model-00003-of-00004.safetensors", "model.decoder.layers.0.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.decoder.layers.0.self_attn.out_proj.bias": "model-00002-of-00004.safetensors", "model.decoder.layers.0.self_attn.out_proj.weight": "model-00002-of-00004.safetensors", "model.decoder.layers.0.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", "model.decoder.layers.0.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.decoder.layers.0.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", "model.decoder.layers.0.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.decoder.layers.0.self_attn_layer_norm.bias": "model-00002-of-00004.safetensors", "model.decoder.layers.0.self_attn_layer_norm.weight": "model-00002-of-00004.safetensors", "model.decoder.layers.1.encoder_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.decoder.layers.1.encoder_attn.out_proj.bias": "model-00003-of-00004.safetensors", "model.decoder.layers.1.encoder_attn.out_proj.weight": "model-00003-of-00004.safetensors", "model.decoder.layers.1.encoder_attn.q_proj.bias": "model-00003-of-00004.safetensors", "model.decoder.layers.1.encoder_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.decoder.layers.1.encoder_attn.v_proj.bias": "model-00003-of-00004.safetensors", "model.decoder.layers.1.encoder_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.decoder.layers.1.encoder_attn_layer_norm.bias": "model-00003-of-00004.safetensors", "model.decoder.layers.1.encoder_attn_layer_norm.weight": "model-00003-of-00004.safetensors", "model.decoder.layers.1.fc1.bias": "model-00003-of-00004.safetensors", "model.decoder.layers.1.fc1.weight": "model-00003-of-00004.safetensors", "model.decoder.layers.1.fc2.bias": "model-00003-of-00004.safetensors", "model.decoder.layers.1.fc2.weight": "model-00003-of-00004.safetensors", "model.decoder.layers.1.final_layer_norm.bias": "model-00003-of-00004.safetensors", "model.decoder.layers.1.final_layer_norm.weight": "model-00003-of-00004.safetensors", "model.decoder.layers.1.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.decoder.layers.1.self_attn.out_proj.bias": "model-00003-of-00004.safetensors", "model.decoder.layers.1.self_attn.out_proj.weight": "model-00003-of-00004.safetensors", "model.decoder.layers.1.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", "model.decoder.layers.1.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.decoder.layers.1.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", "model.decoder.layers.1.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.decoder.layers.1.self_attn_layer_norm.bias": "model-00003-of-00004.safetensors", "model.decoder.layers.1.self_attn_layer_norm.weight": "model-00003-of-00004.safetensors", "model.decoder.layers.2.encoder_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.decoder.layers.2.encoder_attn.out_proj.bias": "model-00003-of-00004.safetensors", "model.decoder.layers.2.encoder_attn.out_proj.weight": "model-00003-of-00004.safetensors", "model.decoder.layers.2.encoder_attn.q_proj.bias": "model-00003-of-00004.safetensors", "model.decoder.layers.2.encoder_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.decoder.layers.2.encoder_attn.v_proj.bias": "model-00003-of-00004.safetensors", "model.decoder.layers.2.encoder_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.decoder.layers.2.encoder_attn_layer_norm.bias": "model-00003-of-00004.safetensors", "model.decoder.layers.2.encoder_attn_layer_norm.weight": "model-00003-of-00004.safetensors", "model.decoder.layers.2.fc1.bias": "model-00003-of-00004.safetensors", "model.decoder.layers.2.fc1.weight": "model-00003-of-00004.safetensors", "model.decoder.layers.2.fc2.bias": "model-00003-of-00004.safetensors", "model.decoder.layers.2.fc2.weight": "model-00003-of-00004.safetensors", "model.decoder.layers.2.final_layer_norm.bias": "model-00003-of-00004.safetensors", "model.decoder.layers.2.final_layer_norm.weight": "model-00003-of-00004.safetensors", "model.decoder.layers.2.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.decoder.layers.2.self_attn.out_proj.bias": "model-00003-of-00004.safetensors", "model.decoder.layers.2.self_attn.out_proj.weight": "model-00003-of-00004.safetensors", "model.decoder.layers.2.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", "model.decoder.layers.2.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.decoder.layers.2.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", "model.decoder.layers.2.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.decoder.layers.2.self_attn_layer_norm.bias": "model-00003-of-00004.safetensors", "model.decoder.layers.2.self_attn_layer_norm.weight": "model-00003-of-00004.safetensors", "model.decoder.layers.3.encoder_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.decoder.layers.3.encoder_attn.out_proj.bias": "model-00003-of-00004.safetensors", "model.decoder.layers.3.encoder_attn.out_proj.weight": "model-00003-of-00004.safetensors", "model.decoder.layers.3.encoder_attn.q_proj.bias": "model-00003-of-00004.safetensors", "model.decoder.layers.3.encoder_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.decoder.layers.3.encoder_attn.v_proj.bias": "model-00003-of-00004.safetensors", "model.decoder.layers.3.encoder_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.decoder.layers.3.encoder_attn_layer_norm.bias": "model-00003-of-00004.safetensors", "model.decoder.layers.3.encoder_attn_layer_norm.weight": "model-00003-of-00004.safetensors", "model.decoder.layers.3.fc1.bias": "model-00003-of-00004.safetensors", "model.decoder.layers.3.fc1.weight": "model-00003-of-00004.safetensors", "model.decoder.layers.3.fc2.bias": "model-00003-of-00004.safetensors", "model.decoder.layers.3.fc2.weight": "model-00003-of-00004.safetensors", "model.decoder.layers.3.final_layer_norm.bias": "model-00003-of-00004.safetensors", "model.decoder.layers.3.final_layer_norm.weight": "model-00003-of-00004.safetensors", "model.decoder.layers.3.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.decoder.layers.3.self_attn.out_proj.bias": "model-00003-of-00004.safetensors", "model.decoder.layers.3.self_attn.out_proj.weight": "model-00003-of-00004.safetensors", "model.decoder.layers.3.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", "model.decoder.layers.3.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.decoder.layers.3.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", "model.decoder.layers.3.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.decoder.layers.3.self_attn_layer_norm.bias": "model-00003-of-00004.safetensors", "model.decoder.layers.3.self_attn_layer_norm.weight": "model-00003-of-00004.safetensors", "model.decoder.layers.4.encoder_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.decoder.layers.4.encoder_attn.out_proj.bias": "model-00003-of-00004.safetensors", "model.decoder.layers.4.encoder_attn.out_proj.weight": "model-00003-of-00004.safetensors", "model.decoder.layers.4.encoder_attn.q_proj.bias": "model-00003-of-00004.safetensors", "model.decoder.layers.4.encoder_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.decoder.layers.4.encoder_attn.v_proj.bias": "model-00003-of-00004.safetensors", "model.decoder.layers.4.encoder_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.decoder.layers.4.encoder_attn_layer_norm.bias": "model-00003-of-00004.safetensors", "model.decoder.layers.4.encoder_attn_layer_norm.weight": "model-00003-of-00004.safetensors", "model.decoder.layers.4.fc1.bias": "model-00003-of-00004.safetensors", "model.decoder.layers.4.fc1.weight": "model-00003-of-00004.safetensors", "model.decoder.layers.4.fc2.bias": "model-00003-of-00004.safetensors", "model.decoder.layers.4.fc2.weight": "model-00003-of-00004.safetensors", "model.decoder.layers.4.final_layer_norm.bias": "model-00003-of-00004.safetensors", "model.decoder.layers.4.final_layer_norm.weight": "model-00003-of-00004.safetensors", "model.decoder.layers.4.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.decoder.layers.4.self_attn.out_proj.bias": "model-00003-of-00004.safetensors", "model.decoder.layers.4.self_attn.out_proj.weight": "model-00003-of-00004.safetensors", "model.decoder.layers.4.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", "model.decoder.layers.4.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.decoder.layers.4.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", "model.decoder.layers.4.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.decoder.layers.4.self_attn_layer_norm.bias": "model-00003-of-00004.safetensors", "model.decoder.layers.4.self_attn_layer_norm.weight": "model-00003-of-00004.safetensors", "model.decoder.layers.5.encoder_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.decoder.layers.5.encoder_attn.out_proj.bias": "model-00004-of-00004.safetensors", "model.decoder.layers.5.encoder_attn.out_proj.weight": "model-00004-of-00004.safetensors", "model.decoder.layers.5.encoder_attn.q_proj.bias": "model-00004-of-00004.safetensors", "model.decoder.layers.5.encoder_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.decoder.layers.5.encoder_attn.v_proj.bias": "model-00004-of-00004.safetensors", "model.decoder.layers.5.encoder_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.decoder.layers.5.encoder_attn_layer_norm.bias": "model-00004-of-00004.safetensors", "model.decoder.layers.5.encoder_attn_layer_norm.weight": "model-00004-of-00004.safetensors", "model.decoder.layers.5.fc1.bias": "model-00004-of-00004.safetensors", "model.decoder.layers.5.fc1.weight": "model-00004-of-00004.safetensors", "model.decoder.layers.5.fc2.bias": "model-00004-of-00004.safetensors", "model.decoder.layers.5.fc2.weight": "model-00004-of-00004.safetensors", "model.decoder.layers.5.final_layer_norm.bias": "model-00004-of-00004.safetensors", "model.decoder.layers.5.final_layer_norm.weight": "model-00004-of-00004.safetensors", "model.decoder.layers.5.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.decoder.layers.5.self_attn.out_proj.bias": "model-00004-of-00004.safetensors", "model.decoder.layers.5.self_attn.out_proj.weight": "model-00004-of-00004.safetensors", "model.decoder.layers.5.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", "model.decoder.layers.5.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.decoder.layers.5.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", "model.decoder.layers.5.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.decoder.layers.5.self_attn_layer_norm.bias": "model-00004-of-00004.safetensors", "model.decoder.layers.5.self_attn_layer_norm.weight": "model-00004-of-00004.safetensors", "model.decoder.layers.6.encoder_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.decoder.layers.6.encoder_attn.out_proj.bias": "model-00004-of-00004.safetensors", "model.decoder.layers.6.encoder_attn.out_proj.weight": "model-00004-of-00004.safetensors", "model.decoder.layers.6.encoder_attn.q_proj.bias": "model-00004-of-00004.safetensors", "model.decoder.layers.6.encoder_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.decoder.layers.6.encoder_attn.v_proj.bias": "model-00004-of-00004.safetensors", "model.decoder.layers.6.encoder_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.decoder.layers.6.encoder_attn_layer_norm.bias": "model-00004-of-00004.safetensors", "model.decoder.layers.6.encoder_attn_layer_norm.weight": "model-00004-of-00004.safetensors", "model.decoder.layers.6.fc1.bias": "model-00004-of-00004.safetensors", "model.decoder.layers.6.fc1.weight": "model-00004-of-00004.safetensors", "model.decoder.layers.6.fc2.bias": "model-00004-of-00004.safetensors", "model.decoder.layers.6.fc2.weight": "model-00004-of-00004.safetensors", "model.decoder.layers.6.final_layer_norm.bias": "model-00004-of-00004.safetensors", "model.decoder.layers.6.final_layer_norm.weight": "model-00004-of-00004.safetensors", "model.decoder.layers.6.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.decoder.layers.6.self_attn.out_proj.bias": "model-00004-of-00004.safetensors", "model.decoder.layers.6.self_attn.out_proj.weight": "model-00004-of-00004.safetensors", "model.decoder.layers.6.self_attn.q_proj.bias": "model-00004-of-00004.safetensors", "model.decoder.layers.6.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.decoder.layers.6.self_attn.v_proj.bias": "model-00004-of-00004.safetensors", "model.decoder.layers.6.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.decoder.layers.6.self_attn_layer_norm.bias": "model-00004-of-00004.safetensors", "model.decoder.layers.6.self_attn_layer_norm.weight": "model-00004-of-00004.safetensors", "model.decoder.layers.7.encoder_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.decoder.layers.7.encoder_attn.out_proj.bias": "model-00004-of-00004.safetensors", "model.decoder.layers.7.encoder_attn.out_proj.weight": "model-00004-of-00004.safetensors", "model.decoder.layers.7.encoder_attn.q_proj.bias": "model-00004-of-00004.safetensors", "model.decoder.layers.7.encoder_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.decoder.layers.7.encoder_attn.v_proj.bias": "model-00004-of-00004.safetensors", "model.decoder.layers.7.encoder_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.decoder.layers.7.encoder_attn_layer_norm.bias": "model-00004-of-00004.safetensors", "model.decoder.layers.7.encoder_attn_layer_norm.weight": "model-00004-of-00004.safetensors", "model.decoder.layers.7.fc1.bias": "model-00004-of-00004.safetensors", "model.decoder.layers.7.fc1.weight": "model-00004-of-00004.safetensors", "model.decoder.layers.7.fc2.bias": "model-00004-of-00004.safetensors", "model.decoder.layers.7.fc2.weight": "model-00004-of-00004.safetensors", "model.decoder.layers.7.final_layer_norm.bias": "model-00004-of-00004.safetensors", "model.decoder.layers.7.final_layer_norm.weight": "model-00004-of-00004.safetensors", "model.decoder.layers.7.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.decoder.layers.7.self_attn.out_proj.bias": "model-00004-of-00004.safetensors", "model.decoder.layers.7.self_attn.out_proj.weight": "model-00004-of-00004.safetensors", "model.decoder.layers.7.self_attn.q_proj.bias": "model-00004-of-00004.safetensors", "model.decoder.layers.7.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.decoder.layers.7.self_attn.v_proj.bias": "model-00004-of-00004.safetensors", "model.decoder.layers.7.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.decoder.layers.7.self_attn_layer_norm.bias": "model-00004-of-00004.safetensors", "model.decoder.layers.7.self_attn_layer_norm.weight": "model-00004-of-00004.safetensors", "model.encoder.conv1.bias": "model-00001-of-00004.safetensors", "model.encoder.conv1.weight": "model-00001-of-00004.safetensors", "model.encoder.conv2.bias": "model-00001-of-00004.safetensors", "model.encoder.conv2.weight": "model-00001-of-00004.safetensors", "model.encoder.embed_positions.weight": "model-00001-of-00004.safetensors", "model.encoder.layer_norm.bias": "model-00002-of-00004.safetensors", "model.encoder.layer_norm.weight": "model-00002-of-00004.safetensors", "model.encoder.layers.0.fc1.bias": "model-00001-of-00004.safetensors", "model.encoder.layers.0.fc1.weight": "model-00001-of-00004.safetensors", "model.encoder.layers.0.fc2.bias": "model-00001-of-00004.safetensors", "model.encoder.layers.0.fc2.weight": "model-00001-of-00004.safetensors", "model.encoder.layers.0.final_layer_norm.bias": "model-00001-of-00004.safetensors", "model.encoder.layers.0.final_layer_norm.weight": "model-00001-of-00004.safetensors", "model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00004.safetensors", "model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00004.safetensors", "model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", "model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", "model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.encoder.layers.0.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors", "model.encoder.layers.0.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors", "model.encoder.layers.1.fc1.bias": "model-00001-of-00004.safetensors", "model.encoder.layers.1.fc1.weight": "model-00001-of-00004.safetensors", "model.encoder.layers.1.fc2.bias": "model-00001-of-00004.safetensors", "model.encoder.layers.1.fc2.weight": "model-00001-of-00004.safetensors", "model.encoder.layers.1.final_layer_norm.bias": "model-00001-of-00004.safetensors", "model.encoder.layers.1.final_layer_norm.weight": "model-00001-of-00004.safetensors", "model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00004.safetensors", "model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00004.safetensors", "model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", "model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", "model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.encoder.layers.1.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors", "model.encoder.layers.1.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors", "model.encoder.layers.2.fc1.bias": "model-00001-of-00004.safetensors", "model.encoder.layers.2.fc1.weight": "model-00001-of-00004.safetensors", "model.encoder.layers.2.fc2.bias": "model-00001-of-00004.safetensors", "model.encoder.layers.2.fc2.weight": "model-00001-of-00004.safetensors", "model.encoder.layers.2.final_layer_norm.bias": "model-00001-of-00004.safetensors", "model.encoder.layers.2.final_layer_norm.weight": "model-00001-of-00004.safetensors", "model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00004.safetensors", "model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00004.safetensors", "model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", "model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", "model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.encoder.layers.2.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors", "model.encoder.layers.2.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors", "model.encoder.layers.3.fc1.bias": "model-00001-of-00004.safetensors", "model.encoder.layers.3.fc1.weight": "model-00001-of-00004.safetensors", "model.encoder.layers.3.fc2.bias": "model-00001-of-00004.safetensors", "model.encoder.layers.3.fc2.weight": "model-00001-of-00004.safetensors", "model.encoder.layers.3.final_layer_norm.bias": "model-00001-of-00004.safetensors", "model.encoder.layers.3.final_layer_norm.weight": "model-00001-of-00004.safetensors", "model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00004.safetensors", "model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00004.safetensors", "model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", "model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", "model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.encoder.layers.3.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors", "model.encoder.layers.3.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors", "model.encoder.layers.4.fc1.bias": "model-00001-of-00004.safetensors", "model.encoder.layers.4.fc1.weight": "model-00001-of-00004.safetensors", "model.encoder.layers.4.fc2.bias": "model-00001-of-00004.safetensors", "model.encoder.layers.4.fc2.weight": "model-00001-of-00004.safetensors", "model.encoder.layers.4.final_layer_norm.bias": "model-00001-of-00004.safetensors", "model.encoder.layers.4.final_layer_norm.weight": "model-00001-of-00004.safetensors", "model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00004.safetensors", "model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00004.safetensors", "model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", "model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", "model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.encoder.layers.4.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors", "model.encoder.layers.4.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors", "model.encoder.layers.5.fc1.bias": "model-00001-of-00004.safetensors", "model.encoder.layers.5.fc1.weight": "model-00001-of-00004.safetensors", "model.encoder.layers.5.fc2.bias": "model-00002-of-00004.safetensors", "model.encoder.layers.5.fc2.weight": "model-00002-of-00004.safetensors", "model.encoder.layers.5.final_layer_norm.bias": "model-00002-of-00004.safetensors", "model.encoder.layers.5.final_layer_norm.weight": "model-00002-of-00004.safetensors", "model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00004.safetensors", "model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00004.safetensors", "model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", "model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", "model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.encoder.layers.5.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors", "model.encoder.layers.5.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors", "model.encoder.layers.6.fc1.bias": "model-00002-of-00004.safetensors", "model.encoder.layers.6.fc1.weight": "model-00002-of-00004.safetensors", "model.encoder.layers.6.fc2.bias": "model-00002-of-00004.safetensors", "model.encoder.layers.6.fc2.weight": "model-00002-of-00004.safetensors", "model.encoder.layers.6.final_layer_norm.bias": "model-00002-of-00004.safetensors", "model.encoder.layers.6.final_layer_norm.weight": "model-00002-of-00004.safetensors", "model.encoder.layers.6.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.encoder.layers.6.self_attn.out_proj.bias": "model-00002-of-00004.safetensors", "model.encoder.layers.6.self_attn.out_proj.weight": "model-00002-of-00004.safetensors", "model.encoder.layers.6.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", "model.encoder.layers.6.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.encoder.layers.6.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", "model.encoder.layers.6.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.encoder.layers.6.self_attn_layer_norm.bias": "model-00002-of-00004.safetensors", "model.encoder.layers.6.self_attn_layer_norm.weight": "model-00002-of-00004.safetensors", "model.encoder.layers.7.fc1.bias": "model-00002-of-00004.safetensors", "model.encoder.layers.7.fc1.weight": "model-00002-of-00004.safetensors", "model.encoder.layers.7.fc2.bias": "model-00002-of-00004.safetensors", "model.encoder.layers.7.fc2.weight": "model-00002-of-00004.safetensors", "model.encoder.layers.7.final_layer_norm.bias": "model-00002-of-00004.safetensors", "model.encoder.layers.7.final_layer_norm.weight": "model-00002-of-00004.safetensors", "model.encoder.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.encoder.layers.7.self_attn.out_proj.bias": "model-00002-of-00004.safetensors", "model.encoder.layers.7.self_attn.out_proj.weight": "model-00002-of-00004.safetensors", "model.encoder.layers.7.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", "model.encoder.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.encoder.layers.7.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", "model.encoder.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.encoder.layers.7.self_attn_layer_norm.bias": "model-00002-of-00004.safetensors", "model.encoder.layers.7.self_attn_layer_norm.weight": "model-00002-of-00004.safetensors" } }