66 lines
1.8 KiB
Markdown
66 lines
1.8 KiB
Markdown
---
|
||
frameworks:
|
||
- Pytorch
|
||
license: Apache License 2.0
|
||
tasks:
|
||
- text-generation
|
||
|
||
#model-type:
|
||
##如 gpt、phi、llama、chatglm、baichuan 等
|
||
#- gpt
|
||
|
||
#domain:
|
||
##如 nlp、cv、audio、multi-modal
|
||
#- nlp
|
||
|
||
#language:
|
||
##语言代码列表 https://help.aliyun.com/document_detail/215387.html?spm=a2c4g.11186623.0.0.9f8d7467kni6Aa
|
||
#- cn
|
||
|
||
#metrics:
|
||
##如 CIDEr、Blue、ROUGE 等
|
||
#- CIDEr
|
||
|
||
#tags:
|
||
##各种自定义，包括 pretrained、fine-tuned、instruction-tuned、RL-tuned 等训练方法和其他
|
||
#- pretrained
|
||
|
||
#tools:
|
||
##如 vllm、fastchat、llamacpp、AdaSeq 等
|
||
#- vllm
|
||
language:
|
||
- zh
|
||
- en
|
||
base_model:
|
||
- TeleAI/TeleChat2-7B-32K
|
||
base_model_relation: finetune
|
||
datasets:
|
||
- liucong/Chinese-DeepSeek-R1-Distill-data-110k-SFT
|
||
- AI-ModelScope/Bespoke-Stratos-17k
|
||
---
|
||
|
||
|
||
该模型是基于TeleChat2 7B基座模型（非32K版）。
|
||
|
||
经过满血版DeepSeek R1蒸馏中文数据集和英文数据集SFT微调而来，可以让星辰大模型TeleChat2 7B拥有思考能力。
|
||
|
||
可点击进入右下角魔搭创空间中体验效果。我们是来自中国电信上海分公司客服中心的魔方算法团队。
|
||
|
||
#### 您可以通过如下git clone命令，或者ModelScope SDK来下载模型
|
||
SDK下载
|
||
```bash
|
||
#安装ModelScope
|
||
pip install modelscope
|
||
```
|
||
```python
|
||
#SDK模型下载
|
||
from modelscope import snapshot_download
|
||
model_dir = snapshot_download('FlyDutch/telechat2-7b-Cot')
|
||
```
|
||
Git下载
|
||
```
|
||
#Git模型下载
|
||
git clone https://www.modelscope.cn/FlyDutch/telechat2-7b-Cot.git
|
||
```
|
||
|
||
<p style="color: lightgrey;">如果您是本模型的贡献者，我们邀请您根据<a href="https://modelscope.cn/docs/ModelScope%E6%A8%A1%E5%9E%8B%E6%8E%A5%E5%85%A5%E6%B5%81%E7%A8%8B%E6%A6%82%E8%A7%88" style="color: lightgrey; text-decoration: underline;">模型贡献文档</a>，及时完善模型卡片内容。</p> |