Text Generation
Transformers
Safetensors
English
llama
text-generation-inference
4-bit precision
gptq
tulu-30B-GPTQ / special_tokens_map.json
TheBloke's picture
Initial GPTQ model commit
440e85b
raw
history blame
96 Bytes
{
"bos_token": "<s>",
"eos_token": "</s>",
"pad_token": "<pad>",
"unk_token": "<unk>"
}