Text Generation
Transformers
PyTorch
English
llama
text-generation-inference
Tulu-30B-SuperHOT-8K-fp16 / generation_config.json
TheBloke's picture
Initial FP16 model commit
d570df4
raw
history blame
137 Bytes
{
"_from_model_config": true,
"bos_token_id": 1,
"eos_token_id": 2,
"pad_token_id": 0,
"transformers_version": "4.30.0.dev0"
}