Text Generation
Transformers
Safetensors
English
llama
text-generation-inference
4-bit precision
gptq
File size: 96 Bytes
2d084a9
 
 
 
 
 
1
2
3
4
5
6
7
{
  "bos_token": "<s>",
  "eos_token": "</s>",
  "pad_token": "[PAD]",
  "unk_token": "<unk>"
}