Text Generation
Transformers
PyTorch
English
llama
text-generation-inference
Inference Endpoints
OpenOrca-Platypus2-13B / generation_config.json
alpindale's picture
Set cache to true
df35f18
raw
history blame
153 Bytes
{
"_from_model_config": true,
"bos_token_id": 1,
"eos_token_id": 2,
"pad_token_id": 0,
"transformers_version": "4.31.0",
"use_cache": true
}