Text Generation
Transformers
Safetensors
llama
text-generation-inference
4-bit precision
gptq
PuddleJumper-13B-GPTQ / added_tokens.json
TheBloke's picture
Initial GPTQ model commit
b310351
raw
history blame
51 Bytes
{
"<|PAD|>": 32001,
"<|end_of_turn|>": 32000
}