Text Generation
Transformers
Safetensors
English
llama
text-generation-inference
4-bit precision
gptq
OpenOrca-Platypus2-13B-GPTQ / added_tokens.json
TheBloke's picture
Initial GPTQ model commit
acf9170
raw
history blame
51 Bytes
{
"<|PAD|>": 32001,
"<|end_of_turn|>": 32000
}