Text Generation
Transformers
English
llama
Inference Endpoints
LoneStriker's picture
ExLLaMA V2 quant of TinyLlama-1.1B-Chat-v0.3-8.0bpw-h8-exl2
29901b1
raw
history blame
69 Bytes
{
"<|im_end|>": 32002,
"<|im_start|>": 32001,
"[PAD]": 32000
}