{ "_name_or_path": "meta-llama/Meta-Llama-3.1-405B-Instruct-FP8", "architectures": [ "LlamaForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": [ 128001, 128008, 128009 ], "hidden_act": "silu", "hidden_size": 16384, "initializer_range": 0.02, "intermediate_size": 53248, "max_position_embeddings": 131072, "mlp_bias": false, "model_type": "llama", "num_attention_heads": 128, "num_hidden_layers": 126, "num_key_value_heads": 8, "pretraining_tp": 1, "quantization_config": { "activation_scale_ub": 1200.0, "modules_to_not_convert": [ "model.layers.0.mlp.down_proj", "model.layers.0.mlp.gate_proj", "model.layers.0.mlp.up_proj", "model.layers.125.mlp.down_proj", "model.layers.125.mlp.gate_proj", "model.layers.125.mlp.up_proj", "model.layers.0.self_attn.k_proj", "model.layers.0.self_attn.o_proj", "model.layers.0.self_attn.q_proj", "model.layers.0.self_attn.v_proj", "model.layers.1.self_attn.k_proj", "model.layers.1.self_attn.o_proj", "model.layers.1.self_attn.q_proj", "model.layers.1.self_attn.v_proj", "model.layers.2.self_attn.k_proj", "model.layers.2.self_attn.o_proj", "model.layers.2.self_attn.q_proj", "model.layers.2.self_attn.v_proj", "model.layers.3.self_attn.k_proj", "model.layers.3.self_attn.o_proj", "model.layers.3.self_attn.q_proj", "model.layers.3.self_attn.v_proj", "model.layers.4.self_attn.k_proj", "model.layers.4.self_attn.o_proj", "model.layers.4.self_attn.q_proj", "model.layers.4.self_attn.v_proj", "model.layers.5.self_attn.k_proj", "model.layers.5.self_attn.o_proj", "model.layers.5.self_attn.q_proj", "model.layers.5.self_attn.v_proj", "model.layers.6.self_attn.k_proj", "model.layers.6.self_attn.o_proj", "model.layers.6.self_attn.q_proj", "model.layers.6.self_attn.v_proj", "model.layers.7.self_attn.k_proj", "model.layers.7.self_attn.o_proj", "model.layers.7.self_attn.q_proj", "model.layers.7.self_attn.v_proj", "model.layers.8.self_attn.k_proj", "model.layers.8.self_attn.o_proj", "model.layers.8.self_attn.q_proj", "model.layers.8.self_attn.v_proj", "model.layers.9.self_attn.k_proj", "model.layers.9.self_attn.o_proj", "model.layers.9.self_attn.q_proj", "model.layers.9.self_attn.v_proj", "model.layers.10.self_attn.k_proj", "model.layers.10.self_attn.o_proj", "model.layers.10.self_attn.q_proj", "model.layers.10.self_attn.v_proj", "model.layers.11.self_attn.k_proj", "model.layers.11.self_attn.o_proj", "model.layers.11.self_attn.q_proj", "model.layers.11.self_attn.v_proj", "model.layers.12.self_attn.k_proj", "model.layers.12.self_attn.o_proj", "model.layers.12.self_attn.q_proj", "model.layers.12.self_attn.v_proj", "model.layers.13.self_attn.k_proj", "model.layers.13.self_attn.o_proj", "model.layers.13.self_attn.q_proj", "model.layers.13.self_attn.v_proj", "model.layers.14.self_attn.k_proj", "model.layers.14.self_attn.o_proj", "model.layers.14.self_attn.q_proj", "model.layers.14.self_attn.v_proj", "model.layers.15.self_attn.k_proj", "model.layers.15.self_attn.o_proj", "model.layers.15.self_attn.q_proj", "model.layers.15.self_attn.v_proj", "model.layers.16.self_attn.k_proj", "model.layers.16.self_attn.o_proj", "model.layers.16.self_attn.q_proj", "model.layers.16.self_attn.v_proj", "model.layers.17.self_attn.k_proj", "model.layers.17.self_attn.o_proj", "model.layers.17.self_attn.q_proj", "model.layers.17.self_attn.v_proj", "model.layers.18.self_attn.k_proj", "model.layers.18.self_attn.o_proj", "model.layers.18.self_attn.q_proj", "model.layers.18.self_attn.v_proj", "model.layers.19.self_attn.k_proj", "model.layers.19.self_attn.o_proj", "model.layers.19.self_attn.q_proj", "model.layers.19.self_attn.v_proj", "model.layers.20.self_attn.k_proj", "model.layers.20.self_attn.o_proj", "model.layers.20.self_attn.q_proj", "model.layers.20.self_attn.v_proj", "model.layers.21.self_attn.k_proj", "model.layers.21.self_attn.o_proj", "model.layers.21.self_attn.q_proj", "model.layers.21.self_attn.v_proj", "model.layers.22.self_attn.k_proj", "model.layers.22.self_attn.o_proj", "model.layers.22.self_attn.q_proj", "model.layers.22.self_attn.v_proj", "model.layers.23.self_attn.k_proj", "model.layers.23.self_attn.o_proj", "model.layers.23.self_attn.q_proj", "model.layers.23.self_attn.v_proj", "model.layers.24.self_attn.k_proj", "model.layers.24.self_attn.o_proj", "model.layers.24.self_attn.q_proj", "model.layers.24.self_attn.v_proj", "model.layers.25.self_attn.k_proj", "model.layers.25.self_attn.o_proj", "model.layers.25.self_attn.q_proj", "model.layers.25.self_attn.v_proj", "model.layers.26.self_attn.k_proj", "model.layers.26.self_attn.o_proj", "model.layers.26.self_attn.q_proj", "model.layers.26.self_attn.v_proj", "model.layers.27.self_attn.k_proj", "model.layers.27.self_attn.o_proj", "model.layers.27.self_attn.q_proj", "model.layers.27.self_attn.v_proj", "model.layers.28.self_attn.k_proj", "model.layers.28.self_attn.o_proj", "model.layers.28.self_attn.q_proj", "model.layers.28.self_attn.v_proj", "model.layers.29.self_attn.k_proj", "model.layers.29.self_attn.o_proj", "model.layers.29.self_attn.q_proj", "model.layers.29.self_attn.v_proj", "model.layers.30.self_attn.k_proj", "model.layers.30.self_attn.o_proj", "model.layers.30.self_attn.q_proj", "model.layers.30.self_attn.v_proj", "model.layers.31.self_attn.k_proj", "model.layers.31.self_attn.o_proj", "model.layers.31.self_attn.q_proj", "model.layers.31.self_attn.v_proj", "model.layers.32.self_attn.k_proj", "model.layers.32.self_attn.o_proj", "model.layers.32.self_attn.q_proj", "model.layers.32.self_attn.v_proj", "model.layers.33.self_attn.k_proj", "model.layers.33.self_attn.o_proj", "model.layers.33.self_attn.q_proj", "model.layers.33.self_attn.v_proj", "model.layers.34.self_attn.k_proj", "model.layers.34.self_attn.o_proj", "model.layers.34.self_attn.q_proj", "model.layers.34.self_attn.v_proj", "model.layers.35.self_attn.k_proj", "model.layers.35.self_attn.o_proj", "model.layers.35.self_attn.q_proj", "model.layers.35.self_attn.v_proj", "model.layers.36.self_attn.k_proj", "model.layers.36.self_attn.o_proj", "model.layers.36.self_attn.q_proj", "model.layers.36.self_attn.v_proj", "model.layers.37.self_attn.k_proj", "model.layers.37.self_attn.o_proj", "model.layers.37.self_attn.q_proj", "model.layers.37.self_attn.v_proj", "model.layers.38.self_attn.k_proj", "model.layers.38.self_attn.o_proj", "model.layers.38.self_attn.q_proj", "model.layers.38.self_attn.v_proj", "model.layers.39.self_attn.k_proj", "model.layers.39.self_attn.o_proj", "model.layers.39.self_attn.q_proj", "model.layers.39.self_attn.v_proj", "model.layers.40.self_attn.k_proj", "model.layers.40.self_attn.o_proj", "model.layers.40.self_attn.q_proj", "model.layers.40.self_attn.v_proj", "model.layers.41.self_attn.k_proj", "model.layers.41.self_attn.o_proj", "model.layers.41.self_attn.q_proj", "model.layers.41.self_attn.v_proj", "model.layers.42.self_attn.k_proj", "model.layers.42.self_attn.o_proj", "model.layers.42.self_attn.q_proj", "model.layers.42.self_attn.v_proj", "model.layers.43.self_attn.k_proj", "model.layers.43.self_attn.o_proj", "model.layers.43.self_attn.q_proj", "model.layers.43.self_attn.v_proj", "model.layers.44.self_attn.k_proj", "model.layers.44.self_attn.o_proj", "model.layers.44.self_attn.q_proj", "model.layers.44.self_attn.v_proj", "model.layers.45.self_attn.k_proj", "model.layers.45.self_attn.o_proj", "model.layers.45.self_attn.q_proj", "model.layers.45.self_attn.v_proj", "model.layers.46.self_attn.k_proj", "model.layers.46.self_attn.o_proj", "model.layers.46.self_attn.q_proj", "model.layers.46.self_attn.v_proj", "model.layers.47.self_attn.k_proj", "model.layers.47.self_attn.o_proj", "model.layers.47.self_attn.q_proj", "model.layers.47.self_attn.v_proj", "model.layers.48.self_attn.k_proj", "model.layers.48.self_attn.o_proj", "model.layers.48.self_attn.q_proj", "model.layers.48.self_attn.v_proj", "model.layers.49.self_attn.k_proj", "model.layers.49.self_attn.o_proj", "model.layers.49.self_attn.q_proj", "model.layers.49.self_attn.v_proj", "model.layers.50.self_attn.k_proj", "model.layers.50.self_attn.o_proj", "model.layers.50.self_attn.q_proj", "model.layers.50.self_attn.v_proj", "model.layers.51.self_attn.k_proj", "model.layers.51.self_attn.o_proj", "model.layers.51.self_attn.q_proj", "model.layers.51.self_attn.v_proj", "model.layers.52.self_attn.k_proj", "model.layers.52.self_attn.o_proj", "model.layers.52.self_attn.q_proj", "model.layers.52.self_attn.v_proj", "model.layers.53.self_attn.k_proj", "model.layers.53.self_attn.o_proj", "model.layers.53.self_attn.q_proj", "model.layers.53.self_attn.v_proj", "model.layers.54.self_attn.k_proj", "model.layers.54.self_attn.o_proj", "model.layers.54.self_attn.q_proj", "model.layers.54.self_attn.v_proj", "model.layers.55.self_attn.k_proj", "model.layers.55.self_attn.o_proj", "model.layers.55.self_attn.q_proj", "model.layers.55.self_attn.v_proj", "model.layers.56.self_attn.k_proj", "model.layers.56.self_attn.o_proj", "model.layers.56.self_attn.q_proj", "model.layers.56.self_attn.v_proj", "model.layers.57.self_attn.k_proj", "model.layers.57.self_attn.o_proj", "model.layers.57.self_attn.q_proj", "model.layers.57.self_attn.v_proj", "model.layers.58.self_attn.k_proj", "model.layers.58.self_attn.o_proj", "model.layers.58.self_attn.q_proj", "model.layers.58.self_attn.v_proj", "model.layers.59.self_attn.k_proj", "model.layers.59.self_attn.o_proj", "model.layers.59.self_attn.q_proj", "model.layers.59.self_attn.v_proj", "model.layers.60.self_attn.k_proj", "model.layers.60.self_attn.o_proj", "model.layers.60.self_attn.q_proj", "model.layers.60.self_attn.v_proj", "model.layers.61.self_attn.k_proj", "model.layers.61.self_attn.o_proj", "model.layers.61.self_attn.q_proj", "model.layers.61.self_attn.v_proj", "model.layers.62.self_attn.k_proj", "model.layers.62.self_attn.o_proj", "model.layers.62.self_attn.q_proj", "model.layers.62.self_attn.v_proj", "model.layers.63.self_attn.k_proj", "model.layers.63.self_attn.o_proj", "model.layers.63.self_attn.q_proj", "model.layers.63.self_attn.v_proj", "model.layers.64.self_attn.k_proj", "model.layers.64.self_attn.o_proj", "model.layers.64.self_attn.q_proj", "model.layers.64.self_attn.v_proj", "model.layers.65.self_attn.k_proj", "model.layers.65.self_attn.o_proj", "model.layers.65.self_attn.q_proj", "model.layers.65.self_attn.v_proj", "model.layers.66.self_attn.k_proj", "model.layers.66.self_attn.o_proj", "model.layers.66.self_attn.q_proj", "model.layers.66.self_attn.v_proj", "model.layers.67.self_attn.k_proj", "model.layers.67.self_attn.o_proj", "model.layers.67.self_attn.q_proj", "model.layers.67.self_attn.v_proj", "model.layers.68.self_attn.k_proj", "model.layers.68.self_attn.o_proj", "model.layers.68.self_attn.q_proj", "model.layers.68.self_attn.v_proj", "model.layers.69.self_attn.k_proj", "model.layers.69.self_attn.o_proj", "model.layers.69.self_attn.q_proj", "model.layers.69.self_attn.v_proj", "model.layers.70.self_attn.k_proj", "model.layers.70.self_attn.o_proj", "model.layers.70.self_attn.q_proj", "model.layers.70.self_attn.v_proj", "model.layers.71.self_attn.k_proj", "model.layers.71.self_attn.o_proj", "model.layers.71.self_attn.q_proj", "model.layers.71.self_attn.v_proj", "model.layers.72.self_attn.k_proj", "model.layers.72.self_attn.o_proj", "model.layers.72.self_attn.q_proj", "model.layers.72.self_attn.v_proj", "model.layers.73.self_attn.k_proj", "model.layers.73.self_attn.o_proj", "model.layers.73.self_attn.q_proj", "model.layers.73.self_attn.v_proj", "model.layers.74.self_attn.k_proj", "model.layers.74.self_attn.o_proj", "model.layers.74.self_attn.q_proj", "model.layers.74.self_attn.v_proj", "model.layers.75.self_attn.k_proj", "model.layers.75.self_attn.o_proj", "model.layers.75.self_attn.q_proj", "model.layers.75.self_attn.v_proj", "model.layers.76.self_attn.k_proj", "model.layers.76.self_attn.o_proj", "model.layers.76.self_attn.q_proj", "model.layers.76.self_attn.v_proj", "model.layers.77.self_attn.k_proj", "model.layers.77.self_attn.o_proj", "model.layers.77.self_attn.q_proj", "model.layers.77.self_attn.v_proj", "model.layers.78.self_attn.k_proj", "model.layers.78.self_attn.o_proj", "model.layers.78.self_attn.q_proj", "model.layers.78.self_attn.v_proj", "model.layers.79.self_attn.k_proj", "model.layers.79.self_attn.o_proj", "model.layers.79.self_attn.q_proj", "model.layers.79.self_attn.v_proj", "model.layers.80.self_attn.k_proj", "model.layers.80.self_attn.o_proj", "model.layers.80.self_attn.q_proj", "model.layers.80.self_attn.v_proj", "model.layers.81.self_attn.k_proj", "model.layers.81.self_attn.o_proj", "model.layers.81.self_attn.q_proj", "model.layers.81.self_attn.v_proj", "model.layers.82.self_attn.k_proj", "model.layers.82.self_attn.o_proj", "model.layers.82.self_attn.q_proj", "model.layers.82.self_attn.v_proj", "model.layers.83.self_attn.k_proj", "model.layers.83.self_attn.o_proj", "model.layers.83.self_attn.q_proj", "model.layers.83.self_attn.v_proj", "model.layers.84.self_attn.k_proj", "model.layers.84.self_attn.o_proj", "model.layers.84.self_attn.q_proj", "model.layers.84.self_attn.v_proj", "model.layers.85.self_attn.k_proj", "model.layers.85.self_attn.o_proj", "model.layers.85.self_attn.q_proj", "model.layers.85.self_attn.v_proj", "model.layers.86.self_attn.k_proj", "model.layers.86.self_attn.o_proj", "model.layers.86.self_attn.q_proj", "model.layers.86.self_attn.v_proj", "model.layers.87.self_attn.k_proj", "model.layers.87.self_attn.o_proj", "model.layers.87.self_attn.q_proj", "model.layers.87.self_attn.v_proj", "model.layers.88.self_attn.k_proj", "model.layers.88.self_attn.o_proj", "model.layers.88.self_attn.q_proj", "model.layers.88.self_attn.v_proj", "model.layers.89.self_attn.k_proj", "model.layers.89.self_attn.o_proj", "model.layers.89.self_attn.q_proj", "model.layers.89.self_attn.v_proj", "model.layers.90.self_attn.k_proj", "model.layers.90.self_attn.o_proj", "model.layers.90.self_attn.q_proj", "model.layers.90.self_attn.v_proj", "model.layers.91.self_attn.k_proj", "model.layers.91.self_attn.o_proj", "model.layers.91.self_attn.q_proj", "model.layers.91.self_attn.v_proj", "model.layers.92.self_attn.k_proj", "model.layers.92.self_attn.o_proj", "model.layers.92.self_attn.q_proj", "model.layers.92.self_attn.v_proj", "model.layers.93.self_attn.k_proj", "model.layers.93.self_attn.o_proj", "model.layers.93.self_attn.q_proj", "model.layers.93.self_attn.v_proj", "model.layers.94.self_attn.k_proj", "model.layers.94.self_attn.o_proj", "model.layers.94.self_attn.q_proj", "model.layers.94.self_attn.v_proj", "model.layers.95.self_attn.k_proj", "model.layers.95.self_attn.o_proj", "model.layers.95.self_attn.q_proj", "model.layers.95.self_attn.v_proj", "model.layers.96.self_attn.k_proj", "model.layers.96.self_attn.o_proj", "model.layers.96.self_attn.q_proj", "model.layers.96.self_attn.v_proj", "model.layers.97.self_attn.k_proj", "model.layers.97.self_attn.o_proj", "model.layers.97.self_attn.q_proj", "model.layers.97.self_attn.v_proj", "model.layers.98.self_attn.k_proj", "model.layers.98.self_attn.o_proj", "model.layers.98.self_attn.q_proj", "model.layers.98.self_attn.v_proj", "model.layers.99.self_attn.k_proj", "model.layers.99.self_attn.o_proj", "model.layers.99.self_attn.q_proj", "model.layers.99.self_attn.v_proj", "model.layers.100.self_attn.k_proj", "model.layers.100.self_attn.o_proj", "model.layers.100.self_attn.q_proj", "model.layers.100.self_attn.v_proj", "model.layers.101.self_attn.k_proj", "model.layers.101.self_attn.o_proj", "model.layers.101.self_attn.q_proj", "model.layers.101.self_attn.v_proj", "model.layers.102.self_attn.k_proj", "model.layers.102.self_attn.o_proj", "model.layers.102.self_attn.q_proj", "model.layers.102.self_attn.v_proj", "model.layers.103.self_attn.k_proj", "model.layers.103.self_attn.o_proj", "model.layers.103.self_attn.q_proj", "model.layers.103.self_attn.v_proj", "model.layers.104.self_attn.k_proj", "model.layers.104.self_attn.o_proj", "model.layers.104.self_attn.q_proj", "model.layers.104.self_attn.v_proj", "model.layers.105.self_attn.k_proj", "model.layers.105.self_attn.o_proj", "model.layers.105.self_attn.q_proj", "model.layers.105.self_attn.v_proj", "model.layers.106.self_attn.k_proj", "model.layers.106.self_attn.o_proj", "model.layers.106.self_attn.q_proj", "model.layers.106.self_attn.v_proj", "model.layers.107.self_attn.k_proj", "model.layers.107.self_attn.o_proj", "model.layers.107.self_attn.q_proj", "model.layers.107.self_attn.v_proj", "model.layers.108.self_attn.k_proj", "model.layers.108.self_attn.o_proj", "model.layers.108.self_attn.q_proj", "model.layers.108.self_attn.v_proj", "model.layers.109.self_attn.k_proj", "model.layers.109.self_attn.o_proj", "model.layers.109.self_attn.q_proj", "model.layers.109.self_attn.v_proj", "model.layers.110.self_attn.k_proj", "model.layers.110.self_attn.o_proj", "model.layers.110.self_attn.q_proj", "model.layers.110.self_attn.v_proj", "model.layers.111.self_attn.k_proj", "model.layers.111.self_attn.o_proj", "model.layers.111.self_attn.q_proj", "model.layers.111.self_attn.v_proj", "model.layers.112.self_attn.k_proj", "model.layers.112.self_attn.o_proj", "model.layers.112.self_attn.q_proj", "model.layers.112.self_attn.v_proj", "model.layers.113.self_attn.k_proj", "model.layers.113.self_attn.o_proj", "model.layers.113.self_attn.q_proj", "model.layers.113.self_attn.v_proj", "model.layers.114.self_attn.k_proj", "model.layers.114.self_attn.o_proj", "model.layers.114.self_attn.q_proj", "model.layers.114.self_attn.v_proj", "model.layers.115.self_attn.k_proj", "model.layers.115.self_attn.o_proj", "model.layers.115.self_attn.q_proj", "model.layers.115.self_attn.v_proj", "model.layers.116.self_attn.k_proj", "model.layers.116.self_attn.o_proj", "model.layers.116.self_attn.q_proj", "model.layers.116.self_attn.v_proj", "model.layers.117.self_attn.k_proj", "model.layers.117.self_attn.o_proj", "model.layers.117.self_attn.q_proj", "model.layers.117.self_attn.v_proj", "model.layers.118.self_attn.k_proj", "model.layers.118.self_attn.o_proj", "model.layers.118.self_attn.q_proj", "model.layers.118.self_attn.v_proj", "model.layers.119.self_attn.k_proj", "model.layers.119.self_attn.o_proj", "model.layers.119.self_attn.q_proj", "model.layers.119.self_attn.v_proj", "model.layers.120.self_attn.k_proj", "model.layers.120.self_attn.o_proj", "model.layers.120.self_attn.q_proj", "model.layers.120.self_attn.v_proj", "model.layers.121.self_attn.k_proj", "model.layers.121.self_attn.o_proj", "model.layers.121.self_attn.q_proj", "model.layers.121.self_attn.v_proj", "model.layers.122.self_attn.k_proj", "model.layers.122.self_attn.o_proj", "model.layers.122.self_attn.q_proj", "model.layers.122.self_attn.v_proj", "model.layers.123.self_attn.k_proj", "model.layers.123.self_attn.o_proj", "model.layers.123.self_attn.q_proj", "model.layers.123.self_attn.v_proj", "model.layers.124.self_attn.k_proj", "model.layers.124.self_attn.o_proj", "model.layers.124.self_attn.q_proj", "model.layers.124.self_attn.v_proj", "model.layers.125.self_attn.k_proj", "model.layers.125.self_attn.o_proj", "model.layers.125.self_attn.q_proj", "model.layers.125.self_attn.v_proj" ], "quant_method": "fbgemm_fp8" }, "rms_norm_eps": 1e-05, "rope_scaling": { "factor": 8.0, "low_freq_factor": 1.0, "high_freq_factor": 4.0, "original_max_position_embeddings": 8192, "rope_type": "llama3" }, "rope_theta": 500000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.43.0.dev0", "use_cache": true, "vocab_size": 128256 }