diff --git a/README.md b/README.md index e2ff30370705820f8b874e18001ae704a5809092..90318d98cc2008c1700ece37ce673cdd5770ad65 100644 --- a/README.md +++ b/README.md @@ -31,6 +31,12 @@ 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 | +| [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 | +| [GLM-4](nlp/llm/glm-4/pytorch) | PyTorch | Torchrun | glm-4-9b-chat | 4.2.0 | +| [MiniCPM](nlp/llm/minicpm/pytorch) | PyTorch | DeepSpeed | MiniCPM-2B-sft-bf16 | 4.2.0 | +| [Phi-3](nlp/llm/phi-3/pytorch) | PyTorch | Torchrun | Phi-3-mini-4k-instruct | 4.2.0 | ### Computer Vision diff --git a/RELEASE.md b/RELEASE.md index b2ebd875b24ee6399b80e6a071bb3609380508d2..a05197ced1fcfc8ca5399b087d034818b7c4a89d 100644 --- a/RELEASE.md +++ b/RELEASE.md @@ -1,5 +1,52 @@ # DeepSparkHub Release Notes +## DeepSparkHub 25.03 Release Notes + +### 特性和增强 + +#### 模型与算法 +● 新增了9个大模型训练示例,涉及MoE-LLaVA,DeepSpeed和LLaMA-Factory工具箱 + +
| 大模型 | ||||
|---|---|---|---|---|
| MoE-LLaVA-Phi2-2.7B(MoE-LLaVA) | +MoE-LLaVA-Qwen-1.8B(MoE-LLaVA) | +MoE-LLaVA-StableLM-1.6B(MoE-LLaVA) | +||
| Yi_6B(DeepSpeed) | +Yi-1.5_6B(DeepSpeed) | +Yi-VL-6B(LLaMA-Factory) | +||
| GLM-4 | +MiniCPM(DeepSpeed) | +Phi-3 | +||