config.json

{
 "_name_or_path": "meta-llama/Meta-Llama-3.1-405B",
 "architectures": [
 "LlamaForCausalLM"
 ],
 "attention_bias": false,
 "attention_dropout": 0.0,
 "bos_token_id": 128000,
 "eos_token_id": 128001,
 "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": {
 "mlp.down_proj": {
 "offload_meta": false,
 "scale_quant_params": {
 "channel_wise": true,
 "group_size": 128,
 "nbits": 8,
 "optimize": false
 },
 "weight_quant_params": {
 "axis": 0,
 "channel_wise": true,
 "group_size": 128,
 "nbits": 4,
 "optimize": true,
 "round_zero": true,
 "view_as_float": false
 },
 "zero_quant_params": {
 "channel_wise": false,
 "group_size": null,
 "nbits": 8,
 "optimize": false
 }
 },
 "mlp.gate_proj": {
 "offload_meta": false,
 "scale_quant_params": {
 "channel_wise": true,
 "group_size": 128,
 "nbits": 8,
 "optimize": false
 },
 "weight_quant_params": {
 "axis": 0,
 "channel_wise": true,
 "group_size": 128,
 "nbits": 4,
 "optimize": true,
 "round_zero": true,
 "view_as_float": false
 },
 "zero_quant_params": {
 "channel_wise": false,
 "group_size": null,
 "nbits": 8,
 "optimize": false
 }
 },
 "mlp.up_proj": {
 "offload_meta": false,
 "scale_quant_params": {
 "channel_wise": true,
 "group_size": 128,
 "nbits": 8,
 "optimize": false
 },
 "weight_quant_params": {
 "axis": 0,
 "channel_wise": true,
 "group_size": 128,
 "nbits": 4,
 "optimize": true,
 "round_zero": true,
 "view_as_float": false
 },
 "zero_quant_params": {
 "channel_wise": false,
 "group_size": null,
 "nbits": 8,
 "optimize": false
 }
 },
 "self_attn.k_proj": {
 "offload_meta": false,
 "scale_quant_params": {
 "channel_wise": true,
 "group_size": 128,
 "nbits": 8,
 "optimize": false
 },
 "weight_quant_params": {
 "axis": 0,
 "channel_wise": true,
 "group_size": 128,
 "nbits": 4,
 "optimize": true,
 "round_zero": true,
 "view_as_float": false
 },
 "zero_quant_params": {
 "channel_wise": false,
 "group_size": null,
 "nbits": 8,
 "optimize": false
 }
 },
 "self_attn.o_proj": {
 "offload_meta": false,
 "scale_quant_params": {
 "channel_wise": true,
 "group_size": 128,
 "nbits": 8,
 "optimize": false
 },
 "weight_quant_params": {
 "axis": 0,
 "channel_wise": true,
 "group_size": 128,
 "nbits": 4,
 "optimize": true,
 "round_zero": true,
 "view_as_float": false
 },
 "zero_quant_params": {
 "channel_wise": false,
 "group_size": null,
 "nbits": 8,
 "optimize": false
 }
 },
 "self_attn.q_proj": {
 "offload_meta": false,
 "scale_quant_params": {
 "channel_wise": true,
 "group_size": 128,
 "nbits": 8,
 "optimize": false
 },
 "weight_quant_params": {
 "axis": 0,
 "channel_wise": true,
 "group_size": 128,
 "nbits": 4,
 "optimize": true,
 "round_zero": true,
 "view_as_float": false
 },
 "zero_quant_params": {
 "channel_wise": false,
 "group_size": null,
 "nbits": 8,
 "optimize": false
 }
 },
 "self_attn.v_proj": {
 "offload_meta": false,
 "scale_quant_params": {
 "channel_wise": true,
 "group_size": 128,
 "nbits": 8,
 "optimize": false
 },
 "weight_quant_params": {
 "axis": 0,
 "channel_wise": true,
 "group_size": 128,
 "nbits": 4,
 "optimize": true,
 "round_zero": true,
 "view_as_float": false
 },
 "zero_quant_params": {
 "channel_wise": false,
 "group_size": null,
 "nbits": 8,
 "optimize": false
 }
 }
 },
 "rms_norm_eps": 1e-05,
 "rope_scaling": {
 "factor": 8.0,
 "high_freq_factor": 4.0,
 "low_freq_factor": 1.0,
 "original_max_position_embeddings": 8192,
 "rope_type": "llama3"
 },
 "rope_theta": 500000.0,
 "tie_word_embeddings": false,
 "torch_dtype": "bfloat16",
 "transformers_version": "4.44.2",
 "use_cache": true,
 "vocab_size": 128256
}