VictorSanh's picture
creating random llama for causal lm
bfcc1c1
raw
history blame
466 Bytes
{
"architectures": [
"LlamaForCausalLM"
],
"bos_token_id": 0,
"eos_token_id": 1,
"hidden_act": "silu",
"hidden_size": 16,
"initializer_range": 0.02,
"intermediate_size": 64,
"model_type": "llama",
"num_attention_heads": 4,
"num_hidden_layers": 2,
"pad_token_id": -1,
"rms_norm_eps": 1e-06,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.27.0.dev0",
"use_cache": true,
"vocab_size": 32000
}