Text Generation
Transformers
PyTorch
English
gpt_neox
text-generation-inference
Inference Endpoints
juewang's picture
first chat model
d68348d
raw
history blame
627 Bytes
{
"_name_or_path": "/root/fm/models/rp_800b_real_fp16",
"architectures": [
"GPTNeoXForCausalLM"
],
"bos_token_id": 0,
"eos_token_id": 0,
"hidden_act": "gelu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 16384,
"layer_norm_eps": 1e-05,
"max_position_embeddings": 2048,
"model_type": "gpt_neox",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"rotary_emb_base": 10000,
"rotary_pct": 1.0,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.28.1",
"use_cache": true,
"use_parallel_residual": false,
"vocab_size": 50432
}