gemma-3-4b-it-quantized-W4A16 / generation_config.json
abhishekchohan's picture
Upload quantized model
d7cabad verified
raw
history blame contribute delete
192 Bytes
{
"_from_model_config": true,
"bos_token_id": 2,
"cache_implementation": "hybrid",
"eos_token_id": [
1,
106
],
"pad_token_id": 0,
"transformers_version": "4.50.0.dev0"
}