{ | |
"_name_or_path": "/mnt/desa_data/meta_llama1/huggingface_13B", | |
"architectures": [ | |
"LlamaForCausalLM" | |
], | |
"attention_bias": false, | |
"bos_token_id": 1, | |
"eos_token_id": 2, | |
"hidden_act": "silu", | |
"hidden_size": 5120, | |
"initializer_range": 0.02, | |
"intermediate_size": 13824, | |
"max_position_embeddings": 2048, | |
"model_type": "llama", | |
"num_attention_heads": 40, | |
"num_hidden_layers": 40, | |
"num_key_value_heads": 40, | |
"pretraining_tp": 1, | |
"quip_params": { | |
"codebook": "E8P12", | |
"codesz": 8, | |
"idx_dtype": "torch.int16", | |
"lora_rank": 0, | |
"outlier_channel_split": false, | |
"rescale_WH": false | |
}, | |
"rms_norm_eps": 1e-06, | |
"rope_scaling": null, | |
"rope_theta": 10000.0, | |
"tie_word_embeddings": false, | |
"torch_dtype": "float16", | |
"transformers_version": "4.34.0", | |
"use_cache": true, | |
"vocab_size": 32000 | |
} | |