From cf52911fed8326dbe3f2781431c25959b175260e Mon Sep 17 00:00:00 2001 From: hiyouga Date: Tue, 16 Apr 2024 02:36:54 +0800 Subject: [PATCH] update readme --- README.md | 2 +- README_zh.md | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index c89598e2..2fc9ba88 100644 --- a/README.md +++ b/README.md @@ -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. diff --git a/README_zh.md b/README_zh.md index fac92600..6564ad4f 100644 --- a/README_zh.md +++ b/README_zh.md @@ -68,7 +68,7 @@ https://github.com/hiyouga/LLaMA-Factory/assets/16256802/ec36a9dd-37f4-4f72-81bd ## 更新日志 -[24/04/16] 我们支持了 **[unsloth](https://github.com/unslothai/unsloth)** 的长序列训练（24GB 可训练 56k 文本）。该方法相比 FlashAttention-2 提供了 **117%** 的训练速度和 **50%** 的显存节约。更多数据请见[此页面](https://github.com/hiyouga/LLaMA-Factory/wiki/Performance-comparison)。 +[24/04/16] 我们支持了 **[unsloth](https://github.com/unslothai/unsloth)** 的长序列训练（24GB 可训练 Llama-2-7B-56k）。该方法相比 FlashAttention-2 提供了 **117%** 的训练速度和 **50%** 的显存节约。更多数据请见[此页面](https://github.com/hiyouga/LLaMA-Factory/wiki/Performance-comparison)。 [24/03/31] 我们支持了 **[ORPO](https://arxiv.org/abs/2403.07691)**。详细用法请参照 `examples/lora_single_gpu`。