{ | |
"_name_or_path": "meta-llama/Llama-3.3-70B-Instruct", | |
"architectures": [ | |
"LlamaForCausalLM" | |
], | |
"attention_bias": false, | |
"attention_dropout": 0.0, | |
"bos_token_id": 128000, | |
"eos_token_id": [ | |
128001, | |
128008, | |
128009 | |
], | |
"head_dim": 128, | |
"hidden_act": "silu", | |
"hidden_size": 8192, | |
"initializer_range": 0.02, | |
"intermediate_size": 28672, | |
"max_position_embeddings": 131072, | |
"mlp_bias": false, | |
"model_type": "llama", | |
"num_attention_heads": 64, | |
"num_hidden_layers": 80, | |
"num_key_value_heads": 8, | |
"pretraining_tp": 1, | |
"quip_params": { | |
"K": 3, | |
"L": 16, | |
"V": 2, | |
"codebook": "bitshift", | |
"codebook_version": 0, | |
"decode_mode": "quantlut_sym", | |
"skip_list": [ | |
"0_v" | |
], | |
"split_for_tp": false, | |
"td_x": 16, | |
"td_y": 16, | |
"tlut_bits": 9 | |
}, | |
"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": "4.46.2", | |
"use_cache": true, | |
"vocab_size": 128256 | |
} | |