WizardLM-7B-Uncensored / config.json
TheBloke's picture
Change use_cache to True which significantly speeds up inference
721f3de
raw
history blame
552 Bytes
{
"_name_or_path": "/workspace/llama-7b-hf",
"architectures": [
"LlamaForCausalLM"
],
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 11008,
"max_position_embeddings": 2048,
"model_type": "llama",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"pad_token_id": 0,
"rms_norm_eps": 1e-06,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.29.0.dev0",
"use_cache": true,
"vocab_size": 32001
}