# Meta-Llama-3.1-8B-Instruct-A8W8-FP8
---



## Model Files

- [act_scales.json](https://paddlenlp.bj.bcebos.com/models/community/meta-llama/Meta-Llama-3.1-8B-Instruct-A8W8-FP8/act_scales.json) (14.0 KB)

- [added_tokens.json](https://paddlenlp.bj.bcebos.com/models/community/meta-llama/Meta-Llama-3.1-8B-Instruct-A8W8-FP8/added_tokens.json) (10.3 KB)

- [config.json](https://paddlenlp.bj.bcebos.com/models/community/meta-llama/Meta-Llama-3.1-8B-Instruct-A8W8-FP8/config.json) (1.3 KB)

- [generation_config.json](https://paddlenlp.bj.bcebos.com/models/community/meta-llama/Meta-Llama-3.1-8B-Instruct-A8W8-FP8/generation_config.json) (148.0 B)

- [model-00001-of-00001.safetensors](https://paddlenlp.bj.bcebos.com/models/community/meta-llama/Meta-Llama-3.1-8B-Instruct-A8W8-FP8/model-00001-of-00001.safetensors) (15.0 GB)

- [model.safetensors.index.json](https://paddlenlp.bj.bcebos.com/models/community/meta-llama/Meta-Llama-3.1-8B-Instruct-A8W8-FP8/model.safetensors.index.json) (176.9 KB)

- [special_tokens_map.json](https://paddlenlp.bj.bcebos.com/models/community/meta-llama/Meta-Llama-3.1-8B-Instruct-A8W8-FP8/special_tokens_map.json) (88.0 B)

- [tokenizer.model](https://paddlenlp.bj.bcebos.com/models/community/meta-llama/Meta-Llama-3.1-8B-Instruct-A8W8-FP8/tokenizer.model) (2.1 MB)

- [tokenizer_config.json](https://paddlenlp.bj.bcebos.com/models/community/meta-llama/Meta-Llama-3.1-8B-Instruct-A8W8-FP8/tokenizer_config.json) (38.3 KB)

- [training_args.bin](https://paddlenlp.bj.bcebos.com/models/community/meta-llama/Meta-Llama-3.1-8B-Instruct-A8W8-FP8/training_args.bin) (2.9 KB)

- [weight_scales.json](https://paddlenlp.bj.bcebos.com/models/community/meta-llama/Meta-Llama-3.1-8B-Instruct-A8W8-FP8/weight_scales.json) (13.4 KB)


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