Skip to content

Commit e8d03f9

Browse files
chencyudelchencyudel
committed
readme
1 parent b45edf2 commit e8d03f9

File tree

2 files changed

+7
-3
lines changed

2 files changed

+7
-3
lines changed

‎README.md

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -50,6 +50,8 @@
5050

5151
🔥🔥🔥 [2024/05/20] Our [MFTCoder Paper](https://arxiv.org/abs/2311.02303) has been accepted by KDD2024.
5252

53+
🔥🔥🔥 [2024/05/20] [CodeFuse-StarCoder2-15B](https://huggingface.co/codefuse-ai/CodeFuse-StarCoder2-15B) has been released, achieving a pass@1 (greedy decoding) score of 73.2% on HumanEval.
54+
5355
🔥🔥 [2024/01/30] The model [CodeFuse-DeepSeek-33B](https://huggingface.co/codefuse-ai/CodeFuse-DeepSeek-33B) fine-tuned with MFTCoder ranks first in HuggingFace [Big Code Models LeaderBoard](https://huggingface.co/spaces/bigcode/bigcode-models-leaderboard)
5456

5557
🔥🔥 [2024/01/17] We released MFTCoder v0.3.0, mainly for MFTCoder-accelerate. It now supports new models like Mixtral(MoE), DeepSeek-coder, chatglm3. It supports FSDP as an option. It also supports Self-paced Loss as a solution for convergence balance in Multitask Fine-tuning.

‎README_cn.md

Lines changed: 5 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -49,11 +49,13 @@
4949

5050
🔥🔥🔥 [2024/05/20] 我们的 [MFTCoder论文](https://arxiv.org/abs/2311.02303) 已被 KDD 2024 接收.
5151

52-
🔥🔥🔥 [2024/01/17] **MFTCoder-v0.3.0**发布。新增对Mixtral(MoE), DeepSeek等模型的支持；新增支持FSDP(Fully Sharded Data Parallel)；新增Self-paced Loss, 支持多任务收敛均衡。 感兴趣详见微信公众号CodeFuse的文章[MFTCoder 重磅升级v0.3.0发布](https://mp.weixin.qq.com/s/xI3f0iUKq9TIIKZ_kMtcQg)
52+
🔥🔥🔥 开源了[CodeFuse-StarCoder2-15B](https://huggingface.co/codefuse-ai/CodeFuse-StarCoder2-15B)模型，在HumanEval上可以达到73.2%，多代码语言能力均衡.
5353

54-
🔥🔥🔥 [2024/01/17] 开源了[CodeFuse-DeepSeek-33B](https://huggingface.co/codefuse-ai/CodeFuse-DeepSeek-33B)模型，在HumanEval pass@1(greedy decoding)上可以达到78.7%。该模型在Big Code榜单的结果近期发布，请关注公众号获取最新信息。
54+
🔥🔥 [2024/01/17] **MFTCoder-v0.3.0**发布。新增对Mixtral(MoE), DeepSeek等模型的支持；新增支持FSDP(Fully Sharded Data Parallel)；新增Self-paced Loss, 支持多任务收敛均衡。 感兴趣详见微信公众号CodeFuse的文章[MFTCoder 重磅升级v0.3.0发布](https://mp.weixin.qq.com/s/xI3f0iUKq9TIIKZ_kMtcQg)
5555

56-
🔥🔥🔥 [2024/01/17] 开源了[CodeFuse-Mixtral-8x7B](https://huggingface.co/codefuse-ai/CodeFuse-Mixtral-8x7B)模型，在HumanEval pass@1(greedy decoding)上可以达到56.1%。感兴趣详见微信公众号CodeFuse的文章[MFTCoder提升Mixtral-8x7B混合专家模型的代码能力实践](https://mp.weixin.qq.com/s/xI3f0iUKq9TIIKZ_kMtcQg)
56+
🔥🔥 [2024/01/17] 开源了[CodeFuse-DeepSeek-33B](https://huggingface.co/codefuse-ai/CodeFuse-DeepSeek-33B)模型，在HumanEval pass@1(greedy decoding)上可以达到78.7%。该模型在Big Code榜单的结果近期发布，请关注公众号获取最新信息。
57+
58+
🔥🔥 [2024/01/17] 开源了[CodeFuse-Mixtral-8x7B](https://huggingface.co/codefuse-ai/CodeFuse-Mixtral-8x7B)模型，在HumanEval pass@1(greedy decoding)上可以达到56.1%。感兴趣详见微信公众号CodeFuse的文章[MFTCoder提升Mixtral-8x7B混合专家模型的代码能力实践](https://mp.weixin.qq.com/s/xI3f0iUKq9TIIKZ_kMtcQg)
5759

5860
🔥🔥 [2023/11/07] [MFTCoder论文](https://arxiv.org/abs/2311.02303)在Arxiv公布，介绍了多任务微调的技术细节。
5961

0 commit comments

Comments
 (0)