Upload 2 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+distill_orpo.png filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,30 +1,29 @@
----
-license: mit
----
-## 数据集
-### 下载   
-```bash
-git lfs install
-git clone https://huggingface.co/datasets/juneup/PKU-SafeRLHF-orpo
-```
-**若不想克隆大型文件：
-```bash
-GIT_LFS_SKIP_SMUDGE=1 git clone https://huggingface.co/datasets/juneup/PKU-SafeRLHF-orpo
-```
-
-## 模型
-
-### 下载
-```bash
-git lfs install
-git clone https://huggingface.co/juneup/internlm2.5_7b_distill_orpo
-```
-**若不想克隆大型文件
-```bash
-GIT_LFS_SKIP_SMUDGE=1 git clone https://huggingface.co/juneup/internlm2.5_7b_distill_orpo
-```
-
-### 在Ollama下载
-```bash
-ollama run Juneup/internlm2.5_7b_distill:orpo_q4_k_m
-```
+# internlm2.5_7b_distill_orpo
+## 架构图
+<div align="center">
+  <img src="distill_orpo.png" width="800"/>
+</div>
+
+## 基座模型
+https://huggingface.co/Slipstream-Max/Emollm-InternLM2.5-7B-chat-GGUF-fp16
+
+## 数据集
+### 数据集组成
+PKU-SafeRLHF(https://huggingface.co/datasets/PKU-Alignment/PKU-SafeRLHF-single-dimension)经处理后最终数据集为(https://huggingface.co/datasets/juneup/PKU-SafeRLHF-orpo)
+
+### 训练方式
+orpo、λ=0.2，lr=5e-6
+
+## 下载模型
+```bash
+git lfs install
+git clone https://huggingface.co/juneup/internlm2.5_7b_distill_orpo
+```
+若不想克隆大型文件
+```bash
+GIT_LFS_SKIP_SMUDGE=1 git clone https://huggingface.co/juneup/internlm2.5_7b_distill_orpo
+```
+
+### 在Ollama下载
+```bash
+ollama run Juneup/internlm2.5_7b_distill:orpo_q4_k_m