Text Generation
Transformers
Safetensors
English
llama
text-generation-inference
4-bit precision
awq
TinyLlama-1.1B-Chat-v0.3-AWQ / generation_config.json
TheBloke's picture
AWQ model commit
7ec57c0
raw
history blame
68 Bytes
{
"max_new_tokens": 32,
"transformers_version": "4.34.0.dev0"
}