seed-llama-8b-pretrain / config.json
tttoaster's picture
upload model
0c47fe7
raw
history blame contribute delete
559 Bytes
{
"_name_or_path": "",
"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": "bfloat16",
"transformers_version": "4.30.2",
"use_cache": false,
"vocab_size": 40194
}