japanese-gpt-neox-3.6b / config.json
tianyuz's picture
init commit
6060312
{
"architectures": [
"GPTNeoXForCausalLM"
],
"bos_token_id": 2,
"eos_token_id": 3,
"hidden_act": "gelu",
"hidden_size": 2816,
"initializer_range": 0.02,
"intermediate_size": 11264,
"layer_norm_eps": 1e-05,
"max_position_embeddings": 2048,
"model_type": "gpt_neox",
"num_attention_heads": 22,
"num_hidden_layers": 36,
"rotary_emb_base": 10000,
"rotary_pct": 1.0,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"use_cache": true,
"use_parallel_residual": false,
"vocab_size": 32000
}