Text Generation
Transformers
Safetensors
English
llama
text-generation-inference
4-bit precision
gptq
TinyLlama-1.1B-Chat-v0.3-GPTQ / special_tokens_map.json
TheBloke's picture
GPTQ model commit
2d084a9
raw
history blame
96 Bytes
{
"bos_token": "<s>",
"eos_token": "</s>",
"pad_token": "[PAD]",
"unk_token": "<unk>"
}