malteos's picture
Upload GPTNeoXForCausalLM
dfb1de2 verified
{
"_name_or_path": "data/continued-pythia-410m/shuffled_dedup_filtered_with_vis_20k-40k/hf_checkpoints/global_step9537",
"architectures": [
"GPTNeoXForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 0,
"classifier_dropout": 0.1,
"eos_token_id": 2,
"hidden_act": "gelu",
"hidden_dropout": 0.0,
"hidden_size": 1024,
"initializer_range": 0.02,
"intermediate_size": 4096,
"layer_norm_eps": 1e-05,
"max_position_embeddings": 2048,
"model_type": "gpt_neox",
"num_attention_heads": 16,
"num_hidden_layers": 24,
"rope_scaling": null,
"rotary_emb_base": 1000.0,
"rotary_pct": 0.25,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.35.2",
"use_cache": true,
"use_parallel_residual": true,
"vocab_size": 50304
}