mtg-aurora / config.json
stillerman's picture
renamed base model
4ca0cc3
{
"_name_or_path": "aurora-m/aurora-m-v0.1-biden-harris-redteamed",
"activation_function": "gelu",
"architectures": [
"GPTBigCodeForCausalLM"
],
"attention_softmax_in_fp32": true,
"attn_pdrop": 0.1,
"bos_token_id": 0,
"embd_pdrop": 0.1,
"eos_token_id": 0,
"initializer_range": 0.02,
"layer_norm_epsilon": 1e-05,
"model_type": "gpt_bigcode",
"multi_query": true,
"n_embd": 6144,
"n_head": 48,
"n_inner": 24576,
"n_layer": 40,
"n_positions": 8192,
"pad_token_id": 0,
"resid_pdrop": 0.1,
"scale_attention_softmax_in_fp32": true,
"scale_attn_weights": true,
"torch_dtype": "float32",
"transformers_version": "4.37.0",
"use_cache": false,
"vocab_size": 49156
}