From 3bc6a925d9aa79b0fe7170243985abca4d5dd6eb Mon Sep 17 00:00:00 2001 From: "hongliang.yuan" Date: Tue, 27 May 2025 10:38:32 +0800 Subject: [PATCH 1/2] add 25.06 release notes --- RELEASE.md | 49 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 49 insertions(+) diff --git a/RELEASE.md b/RELEASE.md index 3e205d31..50087753 100644 --- a/RELEASE.md +++ b/RELEASE.md @@ -1,5 +1,54 @@ # DeepSparkHub Release Notes +## DeepSparkHub 25.06 Release Notes + +### 模型与算法 + +* 新增了1个PyTorch训练模型 +* 新增了5个大模型训练示例，涉及verl和OpenRLHF框架 + + + + + + + + + + + + + + + + + + + + +
PyTorch
YOLOv11
大模型
Llama3-8B PPO(OpenRLHF)Llama3-8B DPO(OpenRLHF)Llama3-8B KTO(OpenRLHF)
Qwen2.5-1.5B(verl)Qwen2.5-7B(verl)
+ +### 问题修复 + +* 优化了AlphaPose模型的冗余代码。 +* 更新了Yi-1.5-6B和Yi-6B模型的文本链接。 +* 增加了中英文README说明。 +* 同步了bloom-7b1、ssd、bert等模型的最新代码 +* 增加了全局模型配置文件。 +* 优化了各模型的README部分表格居中对齐 + +### 版本关联 + +DeepSparkHub 25.06对应天数软件栈4.2.0版本。 + +### 贡献者 + +感谢以下社区贡献者 + +李一力，张文风，majorli6，honglyua，吴永乐。 + +欢迎以任何形式为DeepSparkHub项目贡献。 + ## DeepSparkHub 25.03 Release Notes ### 模型与算法 -- Gitee From 58285d05798c64d7c7785b5c870d011daa132184 Mon Sep 17 00:00:00 2001 From: "hongliang.yuan" Date: Tue, 27 May 2025 10:56:10 +0800 Subject: [PATCH 2/2] add 25.06 model into readme and config --- README.md | 6 +++ README_en.md | 6 +++ tests/model_info.json | 96 +++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 108 insertions(+) diff --git a/README.md b/README.md index 494ad536..ccf43a55 100644 --- a/README.md +++ b/README.md @@ -35,6 +35,9 @@ DeepSparkHub甄选上百个应用算法和模型，覆盖AI和通用计算各领 | [Llama2-34B](nlp/llm/llama2-34b/pytorch) | PyTorch | Megatron-DeepSpeed | Bookcorpus | 3.4.0 | | [Llama3-8B](nlp/llm/llama3_8b/pytorch) | PyTorch | Megatron-DeepSpeed | Bookcorpus | 4.1.1 | | [Llama3-8B SFT](nlp/llm/llama3_8b_sft/pytorch) | PyTorch | ColossalAI | school_math_0.25M | 4.1.1 | +| [Llama3-8B PPO](nlp/llm/llama3_8b/openrlhf) | PyTorch | OpenRLHF | Llama-3-8b-sft-mixture | 4.2.0 | +| [Llama3-8B DPO](nlp/llm/llama3_8b/openrlhf) | PyTorch | OpenRLHF | Llama-3-8b-sft-mixture | 4.2.0 | +| [Llama3-8B KTO](nlp/llm/llama3_8b/openrlhf) | PyTorch | OpenRLHF | Llama-3-8b-sft-mixture | 4.2.0 | | [Mamba-2](nlp/llm/mamba-2/pytorch) | PyTorch | Megatron-LM | GPT Small-117M | 4.1.1 | | [MiniCPM](nlp/llm/minicpm/pytorch) | PyTorch | DeepSpeed | MiniCPM-2B-sft-bf16 | 4.2.0 | | [Mixtral 8x7B](nlp/llm/mixtral/pytorch) | PyTorch | Megatron-LM | GPT Small-117M | 4.1.1 | @@ -43,6 +46,8 @@ DeepSparkHub甄选上百个应用算法和模型，覆盖AI和通用计算各领 | [QWen1.5-7B](nlp/llm/qwen1.5-7b/pytorch) | PyTorch | Firefly | school_math | 4.1.1 | | [QWen1.5-14B](nlp/llm/qwen1.5-14b/pytorch) | PyTorch | Firefly | school_math | 4.1.1 | | [Qwen2.5-7B SFT](nlp/llm/qwen2.5-7b/pytorch) | PyTorch | LLaMA-Factory | qwen2.5-7b | 4.1.1 | +| [Qwen2.5-1.5B verl](nlp/llm/qwen2.5-1.5b/verl) | PyTorch | verl | qwen2.5-1.5b | 4.2.0 | +| [Qwen2.5-7B verl](nlp/llm/qwen2.5-7b/verl) | PyTorch | verl | qwen2.5-7b | 4.2.0 | | [Yi-6B](nlp/llm/yi-6b/pytorch) | PyTorch | DeepSpeed | Yi-6B | 4.2.0 | | [Yi-1.5-6B](nlp/llm/yi-1.5-6b/pytorch) | PyTorch | DeepSpeed | Yi-1.5-6B | 4.2.0 | | [Yi-VL-6B](nlp/llm/yi-vl-6b/pytorch) | PyTorch | LLaMA-Factory | Yi-VL-6B-hf | 4.2.0 | @@ -206,6 +211,7 @@ DeepSparkHub甄选上百个应用算法和模型，覆盖AI和通用计算各领 | [YOLOv8](cv/detection/yolov8/pytorch) | PyTorch | COCO | 3.0.0 | | [YOLOv9](cv/detection/yolov9/pytorch) | PyTorch | COCO | 4.1.1 | | [YOLOv10](cv/detection/yolov10/pytorch) | PyTorch | COCO | 4.1.1 | +| [YOLOv11](cv/detection/yolov11/pytorch) | PyTorch | COCO | 4.2.0 | #### 三维目标检测 diff --git a/README_en.md b/README_en.md index 255003a0..3f3d59f0 100644 --- a/README_en.md +++ b/README_en.md @@ -37,6 +37,9 @@ individuals, healthcare, education, communication, energy, and more. | [Llama2-34B](nlp/llm/llama2-34b/pytorch) | PyTorch | Megatron-DeepSpeed | Bookcorpus | 3.4.0 | | [Llama3-8B](nlp/llm/llama3_8b/pytorch) | PyTorch | Megatron-DeepSpeed | Bookcorpus | 4.1.1 | | [Llama3-8B SFT](nlp/llm/llama3_8b_sft/pytorch) | PyTorch | ColossalAI | school_math_0.25M | 4.1.1 | +| [Llama3-8B PPO](nlp/llm/llama3_8b/openrlhf) | PyTorch | OpenRLHF | Llama-3-8b-sft-mixture | 4.2.0 | +| [Llama3-8B DPO](nlp/llm/llama3_8b/openrlhf) | PyTorch | OpenRLHF | Llama-3-8b-sft-mixture | 4.2.0 | +| [Llama3-8B KTO](nlp/llm/llama3_8b/openrlhf) | PyTorch | OpenRLHF | Llama-3-8b-sft-mixture | 4.2.0 | | [Mamba-2](nlp/llm/mamba-2/pytorch) | PyTorch | Megatron-LM | GPT Small-117M | 4.1.1 | | [MiniCPM](nlp/llm/minicpm/pytorch) | PyTorch | DeepSpeed | MiniCPM-2B-sft-bf16 | 4.2.0 | | [Mixtral 8x7B](nlp/llm/mixtral/pytorch) | PyTorch | Megatron-LM | GPT Small-117M | 4.1.1 | @@ -45,6 +48,8 @@ individuals, healthcare, education, communication, energy, and more. | [QWen1.5-7B](nlp/llm/qwen1.5-7b/pytorch) | PyTorch | Firefly | school_math | 4.1.1 | | [QWen1.5-14B](nlp/llm/qwen1.5-14b/pytorch) | PyTorch | Firefly | school_math | 4.1.1 | | [Qwen2.5-7B SFT](nlp/llm/qwen2.5-7b/pytorch) | PyTorch | LLaMA-Factory | qwen2.5-7b | 4.1.1 | +| [Qwen2.5-1.5B verl](nlp/llm/qwen2.5-1.5b/verl) | PyTorch | verl | qwen2.5-1.5b | 4.2.0 | +| [Qwen2.5-7B verl](nlp/llm/qwen2.5-7b/verl) | PyTorch | verl | qwen2.5-7b | 4.2.0 | | [Yi-6B](nlp/llm/yi-6b/pytorch) | PyTorch | DeepSpeed | Yi-6B | 4.2.0 | | [Yi-1.5-6B](nlp/llm/yi-1.5-6b/pytorch) | PyTorch | DeepSpeed | Yi-1.5-6B | 4.2.0 | | [Yi-VL-6B](nlp/llm/yi-vl-6b/pytorch) | PyTorch | LLaMA-Factory | Yi-VL-6B-hf | 4.2.0 | @@ -208,6 +213,7 @@ individuals, healthcare, education, communication, energy, and more. | [YOLOv8](cv/detection/yolov8/pytorch) | PyTorch | COCO | 3.0.0 | | [YOLOv9](cv/detection/yolov9/pytorch) | PyTorch | COCO | 4.1.1 | | [YOLOv10](cv/detection/yolov10/pytorch) | PyTorch | COCO | 4.1.1 | +| [YOLOv11](cv/detection/yolov11/pytorch) | PyTorch | COCO | 4.2.0 | #### 3D Object Detection diff --git a/tests/model_info.json b/tests/model_info.json index 8d6dde1c..a5b2b6f7 100644 --- a/tests/model_info.json +++ b/tests/model_info.json @@ -7247,6 +7247,102 @@ "github_branch": "", "github_path": "", "priority": "P4" + }, + { + "model_name": "yolov11", + "framework": "pytorch", + "release_version": "25.06", + "release_sdk": "4.2.0", + "release_gpgpu": "BI-V150", + "latest_sdk": "", + "latest_gpgpu": "", + "category": "cv/detection", + "toolbox": "", + "mdims": "", + "dataset": "", + "license": "", + "model_path": "deepsparkhub/cv/detection/yolov11/pytorch/", + "readme_file": "deepsparkhub/cv/detection/yolov11/pytorch/README.md", + "bitbucket_repo": "", + "bitbucket_branch": "", + "bitbucket_path": "", + "develop_owner": "", + "github_repo": "", + "github_branch": "", + "github_path": "", + "priority": "P4" + }, + { + "model_name": "llama3_8b", + "framework": "pytorch", + "release_version": "25.06", + "release_sdk": "4.2.0", + "release_gpgpu": "BI-V150", + "latest_sdk": "", + "latest_gpgpu": "", + "category": "nlp/llm", + "toolbox": "openrlhf", + "mdims": "", + "dataset": "", + "license": "", + "model_path": "deepsparkhub/nlp/llm/llama3_8b/openrlhf", + "readme_file": "deepsparkhub/nlp/llm/llama3_8b/openrlhf/README.md", + "bitbucket_repo": "", + "bitbucket_branch": "", + "bitbucket_path": "", + "develop_owner": "", + "github_repo": "", + "github_branch": "", + "github_path": "", + "priority": "P4" + }, + { + "model_name": "qwen2.5-1.5b", + "framework": "pytorch", + "release_version": "25.06", + "release_sdk": "4.2.0", + "release_gpgpu": "BI-V150", + "latest_sdk": "", + "latest_gpgpu": "", + "category": "nlp/llm", + "toolbox": "verl", + "mdims": "", + "dataset": "", + "license": "", + "model_path": "deepsparkhub/nlp/llm/qwen2.5-1.5b/verl/", + "readme_file": "deepsparkhub/nlp/llm/qwen2.5-1.5b/verl/README.md", + "bitbucket_repo": "", + "bitbucket_branch": "", + "bitbucket_path": "", + "develop_owner": "", + "github_repo": "", + "github_branch": "", + "github_path": "", + "priority": "P4" + }, + { + "model_name": "qwen2.5-7b", + "framework": "pytorch", + "release_version": "25.06", + "release_sdk": "4.2.0", + "release_gpgpu": "BI-V150", + "latest_sdk": "", + "latest_gpgpu": "", + "category": "nlp/llm", + "toolbox": "", + "mdims": "", + "dataset": "", + "license": "", + "model_path": "deepsparkhub/nlp/llm/qwen2.5-7b/verl/", + "readme_file": "deepsparkhub/nlp/llm/qwen2.5-7b/verl/README.md", + "bitbucket_repo": "", + "bitbucket_branch": "", + "bitbucket_path": "", + "develop_owner": "", + "github_repo": "", + "github_branch": "", + "github_path": "", + "priority": "P4" } ] } \ No newline at end of file -- Gitee