# llama-7b-wint4
---



## Model Files

- [config.json](https://paddlenlp.bj.bcebos.com/models/community/facebook/llama-7b-wint4/config.json) (1.0 KB)

- [generation_config.json](https://paddlenlp.bj.bcebos.com/models/community/facebook/llama-7b-wint4/generation_config.json) (167.0 B)

- [model.safetensors](https://paddlenlp.bj.bcebos.com/models/community/facebook/llama-7b-wint4/model.safetensors) (3.5 GB)

- [sentencepiece.bpe.model](https://paddlenlp.bj.bcebos.com/models/community/facebook/llama-7b-wint4/sentencepiece.bpe.model) (488.0 KB)

- [special_tokens_map.json](https://paddlenlp.bj.bcebos.com/models/community/facebook/llama-7b-wint4/special_tokens_map.json) (63.0 B)

- [tokenizer_config.json](https://paddlenlp.bj.bcebos.com/models/community/facebook/llama-7b-wint4/tokenizer_config.json) (207.0 B)


[Back to Main](../../)