Nov 13, 2024 · Oct 28, 2024 · Oct 28, 2024 · Oct 28, 2024 · Oct 29, 2024 · Oct 29, 2024
diff --git a/README.md b/README.md
diff --git a/README_cn.md b/README_cn.md
diff --git a/requirements.txt b/requirements.txt
Original file line number	Diff line number	Diff line change
Expand Up		@@ -46,7 +46,9 @@


		## News
	🔥🔥🔥 [2024年10月29日] Our paper [CoBa: Convergence Balancer for Multitask Finetuning of Large Language Models](https://arxiv.org/abs/2410.06741) has been accepted by EMNLP-2024, which achieves balanced convergence across various tasks.
	🔥🔥🔥 [2024年11月01日] We released MFTCoder v0.5 mainly for MFTCoder-accelerate, which is now supporting preference alignment methods like DPO/RPO/ORPO in the new xxpo module, adding full-parameter continue-training in the additional mpt module along with its offline_tokenization module, updating selfpaced method to new convergence balance(CoBa) method for MFT in the original pefts module.

	🔥🔥🔥 [2024年11月01日] Our paper [CoBa: Convergence Balancer for Multitask Finetuning of Large Language Models](https://arxiv.org/abs/2410.06741) has been accepted by EMNLP-2024, which achieves balanced convergence across various tasks.

		🔥🔥🔥 [2024年05月20日] We released MFTCoder v0.4, mainly for MFTCoder-accelerate. It supports QLoRA + DeepSpeed Zero3 and QLoRA + FSDP as options allowing you training very large models. It now supports new models like Qwen2, Qwen2-MoE, Starcoder2, Gemma, etc.

Expand Down
Original file line number	Diff line number	Diff line change
Expand Up		@@ -45,7 +45,9 @@


		## 新闻
	🔥🔥🔥 [2024年10月29日] 我们的论文 [CoBa: Convergence Balancer for Multitask Finetuning of Large Language Models](https://arxiv.org/abs/2410.06741) 已被 EMNLP 2024 接收,可以实现多任务收敛均衡。
	🔥🔥🔥 [2024年11月01日] MFTCoder-v0.5发布,新增xxpo模块支持偏好对齐DPO/RPO/ORPO;新增mpt和offline_tokenization模块支持全量参数的加训;在原本的pefts模块(MFT)更新selfpaced收敛均衡技术并更名CoBa。

	🔥🔥🔥 [2024年11月01日] 我们的论文 [CoBa: Convergence Balancer for Multitask Finetuning of Large Language Models](https://arxiv.org/abs/2410.06741) 已被 EMNLP 2024 接收,可以实现多任务收敛均衡。

		🔥🔥🔥 [2024年05月20日] MFTCoder-v0.4发布。新增支持QLoRA+ DeepSpeed Zero3, QLoRA + FSDP训练模式,可以更好的支持微调更大的模型,比如Qwen1.5-70B等。新增对Qwen2, Qwen2-MoE, Starcoder2, Gemma等模型的支持。

Expand Down