LLaMA-65B-AWQ / config.json
TheBloke's picture
AWQ model commit
6206723
raw
history blame
569 Bytes
{
"architectures": [
"LlamaForCausalLM"
],
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 8192,
"initializer_range": 0.02,
"intermediate_size": 22016,
"max_sequence_length": 2048,
"model_type": "llama",
"num_attention_heads": 64,
"num_hidden_layers": 80,
"pad_token_id": 0,
"rms_norm_eps": 1e-05,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.28.0.dev0",
"use_cache": true,
"vocab_size": 32000,
"pretraining_tp": 1
}