Upload 2 files

README.md

@@ -1,35 +1,28 @@
----
-license: mit
----
-# internlm2.5_7b_distill 
-## 架构图
-<div align="center">
-  <img src="distill.png" width="800"/>
-</div>
-
-## 基座模型
-[internlm2.6-7b-chat](https://huggingface.co/internlm/internlm2_5-7b-chat)
-
-## 数据集
-### 数据集组成
-5k条精选通用领域含思维链数据(https://huggingface.co/datasets/Congliu/Chinese-DeepSeek-R1-Distill-data-110k-SFT)+3k条含思维链心理辅导对话(https://huggingface.co/datasets/CAS-SIAT-XinHai/CPsyCoun)
-
-1. 110k的数据怎么挑选10k条？：基于score
-2. 3k条心理辅导对话：原始对话（alpaca，含history字段，不含思维链，来自于CPsyCounD），使用deepseek r1【通过设置max_token实现低成本获取思维链】给output增加思维链，获得含思维链的数据集
-
-### 训练方式
-qlora，变长注意力，数据拼接
-
-## 下载模型
-```bash
-git lfs install
-git clone https://huggingface.co/juneup/internlm2.5_7b_distill
-```
-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
-```
-
-### 在Ollama下载
-```bash
-ollama run Juneup/internlm2.5_7b_distill:q4_k_m
+---
+license: mit
+---
+# internlm2.5_7b_distill 
+## Architecture
+<div align="center">
+  <img src="distill.png" width="800"/>
+</div>
+
+## Base model
+[internlm2_5-7b-chat](https://huggingface.co/internlm/internlm2_5-7b-chat)
+
+## Datasets used for training
+[10k deepseek R1 general distillation datasets + 3k psychological counseling dialogue distillation datasets](https://huggingface.co/datasets/juneup/psy-mix-gen-distill-13k)
+
+## Download model
+```bash
+git lfs install
+git clone https://huggingface.co/juneup/internlm2.5_7b_distill
+```
+If you want to clone without large files - just their pointers
+```bash
+GIT_LFS_SKIP_SMUDGE=1 git clone https://huggingface.co/juneup/internlm2.5_7b_distill
+```
+
+### Download at Ollama
+```bash
+ollama run Juneup/internlm2.5_7b_distill:q4_k_m