oasst-sft-1-pythia-12b / config.json
andreaskoepf's picture
Upload GPTNeoXForCausalLM
7dcc303
raw
history blame contribute delete
689 Bytes
{
"_name_or_path": "/home/ubuntu/Open-Assistant/model/model_training/.saved_models/oasst-sft-1_12b/checkpoint-7500/",
"architectures": [
"GPTNeoXForCausalLM"
],
"bos_token_id": 0,
"eos_token_id": 0,
"hidden_act": "gelu",
"hidden_size": 5120,
"initializer_range": 0.02,
"intermediate_size": 20480,
"layer_norm_eps": 1e-05,
"max_position_embeddings": 2048,
"model_type": "gpt_neox",
"num_attention_heads": 40,
"num_hidden_layers": 36,
"rotary_emb_base": 10000,
"rotary_pct": 0.25,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.26.1",
"use_cache": true,
"use_parallel_residual": true,
"vocab_size": 50288
}