ros/LLaMA-Factory
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

update readme

Browse Source 
Former-commit-id: 8f233745c3aa7a6ef57f275bec80ee731ff76de3
This commit is contained in:
hiyouga
2024-04-16 02:36:54 +08:00
parent ebf0f4a77c
commit b053c6454e
2 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
README.md
View File

@@ -68,7 +68,7 @@ Compared to ChatGLM's [P-Tuning](https://github.com/THUDM/ChatGLM2-6B/tree/main/
## Changelog
[24/04/16] We supported **[unsloth](https://github.com/unslothai/unsloth)**'s long-sequence training (56k within 24GB). It achieves **117%** speed and **50%** memory compared with FlashAttention-2, more benchmarks can be found in [this page](https://github.com/hiyouga/LLaMA-Factory/wiki/Performance-comparison).
[24/04/16] We supported **[unsloth](https://github.com/unslothai/unsloth)**'s long-sequence training (Llama-2-7B-56k within 24GB). It achieves **117%** speed and **50%** memory compared with FlashAttention-2, more benchmarks can be found in [this page](https://github.com/hiyouga/LLaMA-Factory/wiki/Performance-comparison).
[24/03/31] We supported **[ORPO](https://arxiv.org/abs/2403.07691)**. See `examples/lora_single_gpu` for usage.