llama-7B-alpaca-30p / config.json
lcw99's picture
Upload LlamaForCausalLM
a56d504
raw
history blame
620 Bytes
{
"_name_or_path": "/home/chang/AI/llm/t5tests/gpt-j/Models/llama-7B-en-alpaca",
"architectures": [
"LlamaForCausalLM"
],
"bos_token_id": 0,
"eos_token_id": 1,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 11008,
"max_position_embeddings": 2048,
"max_sequence_length": 2048,
"model_type": "llama",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"pad_token_id": 1,
"rms_norm_eps": 1e-06,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.28.0.dev0",
"use_cache": false,
"vocab_size": 32000
}