Dan Fu
v16
27c0e7c
{
"_name_or_path": "togethercomputer/GPT-NeoXT-Chat-Base-20B",
"architectures": [
"GPTNeoXForCausalLM"
],
"attention_probs_dropout_prob": 0,
"bos_token_id": 0,
"eos_token_id": 0,
"hidden_act": "gelu_fast",
"hidden_dropout_prob": 0,
"hidden_size": 6144,
"initializer_range": 0.02,
"intermediate_size": 24576,
"layer_norm_eps": 1e-05,
"max_position_embeddings": 2048,
"model_type": "gpt_neox",
"num_attention_heads": 64,
"num_hidden_layers": 44,
"rotary_emb_base": 10000,
"rotary_pct": 0.25,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.21.1",
"use_cache": true,
"vocab_size": 50432
}