togethercomputer
/

LLaMA-2-7B-32K

Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

LLaMA-2-7B-32K / modeling_flash_llama.py

Commit History

Add _support_flash_attn_2 to Llama 2 32k (#37)

061211f
verified

arshzahed commited on Mar 27

Correct the output dtype of rmsnorm_func (#13)

aef6d89

ag0 commited on Aug 5, 2023

remove torch.jit

4ec6edc

juewang commited on Aug 3, 2023

init

cf6ad2b

juewang commited on Jul 26, 2023