Text Generation
Transformers
Safetensors
English
llama
text-generation-inference
4-bit precision
gptq
orca_mini_13B-GPTQ / special_tokens_map.json
TheBloke's picture
Initial GPTQ model commit
afc9059
raw
history blame
208 Bytes
{
"bos_token": "<s>",
"eos_token": "</s>",
"pad_token": "</s>",
"unk_token": {
"content": "<unk>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
}
}