DeepSeek-R1-Distill-Llama-70B / generation_config.json
danielhanchen's picture
Upload LlamaForCausalLM
8b7e589 verified
raw
history blame
205 Bytes
{
"_from_model_config": true,
"bos_token_id": 128000,
"eos_token_id": [
128001,
128008,
128009
],
"max_length": 131072,
"pad_token_id": 128004,
"transformers_version": "4.48.0"
}