# Qwen2-7B-Instruct-A8W8-FP8
---



## Model Files

- [act_scales.json](https://paddlenlp.bj.bcebos.com/models/community/Qwen/Qwen2-7B-Instruct-A8W8-FP8/act_scales.json) (12.1 KB)

- [added_tokens.json](https://paddlenlp.bj.bcebos.com/models/community/Qwen/Qwen2-7B-Instruct-A8W8-FP8/added_tokens.json) (71.0 B)

- [config.json](https://paddlenlp.bj.bcebos.com/models/community/Qwen/Qwen2-7B-Instruct-A8W8-FP8/config.json) (873.0 B)

- [generation_config.json](https://paddlenlp.bj.bcebos.com/models/community/Qwen/Qwen2-7B-Instruct-A8W8-FP8/generation_config.json) (207.0 B)

- [model-00001-of-00001.safetensors](https://paddlenlp.bj.bcebos.com/models/community/Qwen/Qwen2-7B-Instruct-A8W8-FP8/model-00001-of-00001.safetensors) (14.2 GB)

- [model.safetensors.index.json](https://paddlenlp.bj.bcebos.com/models/community/Qwen/Qwen2-7B-Instruct-A8W8-FP8/model.safetensors.index.json) (161.7 KB)

- [special_tokens_map.json](https://paddlenlp.bj.bcebos.com/models/community/Qwen/Qwen2-7B-Instruct-A8W8-FP8/special_tokens_map.json) (466.0 B)

- [tokenizer_config.json](https://paddlenlp.bj.bcebos.com/models/community/Qwen/Qwen2-7B-Instruct-A8W8-FP8/tokenizer_config.json) (1.2 KB)

- [training_args.bin](https://paddlenlp.bj.bcebos.com/models/community/Qwen/Qwen2-7B-Instruct-A8W8-FP8/training_args.bin) (2.9 KB)

- [vocab.json](https://paddlenlp.bj.bcebos.com/models/community/Qwen/Qwen2-7B-Instruct-A8W8-FP8/vocab.json) (2.6 MB)

- [weight_scales.json](https://paddlenlp.bj.bcebos.com/models/community/Qwen/Qwen2-7B-Instruct-A8W8-FP8/weight_scales.json) (11.7 KB)


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