quantized-llama-70B / generation_config.json
medmekk's picture
medmekk HF staff
Upload quantized LLaMA 70B model
1718f6a verified
raw
history blame contribute delete
185 Bytes
{
"_from_model_config": true,
"bos_token_id": 128000,
"do_sample": true,
"eos_token_id": 128001,
"temperature": 0.6,
"top_p": 0.9,
"transformers_version": "4.46.0.dev0"
}