Update README.md
Browse files
README.md
CHANGED
|
@@ -20,7 +20,14 @@ ChatYuan-large-v2是一个支持中英双语的功能型对话语言大模型。
|
|
| 20 |
ChatYuan-large-v2 is a functional dialogue language model that supports bilingual Chinese and English.
|
| 21 |
ChatYuan-large-v2 uses the same technical solution as the v1 version, and has been optimized in terms of instruct-tuning, human feedback reinforcement learning and chain-of-thought.
|
| 22 |
|
| 23 |
-
ChatYuan-large-v2
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 24 |
|
| 25 |
在chatyuan-large-v1的原有功能的基础上，我们给模型进行了如下优化：
|
| 26 |
- 增强了基础能力。原有上下文问答、创意性写作能力明显提升。
|
|
@@ -56,12 +63,6 @@ Based on the original functions of Chatyuan-large-v1, we optimized the model as
|
|
| 56 |
|
| 57 |
<a href='https://www.cluebenchmarks.com/clueai.html'>PromptCLUE-large</a>在1000亿token中文语料上预训练，累计学习1.5万亿中文token，并且在数百种任务上进行Prompt任务式训练。针对理解类任务，如分类、情感分析、抽取等，可以自定义标签体系；针对多种生成任务，可以进行采样自由生成。
|
| 58 |
|
| 59 |
-
<a href='https://huggingface.co/spaces/ClueAI/ChatYuan-large-v2' target="__blank">在线Demo huggingface space </a> |
|
| 60 |
-
<a href='https://www.clueai.cn' target="__blank">使用API(large版)</a> |
|
| 61 |
-
<a href='https://github.com/clue-ai/ChatYuan' target="__blank">Github项目地址</a> |
|
| 62 |
-
<a href='https://colab.research.google.com/drive/1ZcLIJuemiojigrfjbsDMBWrX7JqXZX6I?usp=sharing' target="__blank">Colab在线试用</a> |
|
| 63 |
-
<a href='https://mp.weixin.qq.com/s/-axa6XcjGl_Koeq_OrDq8w' target="__blank">文章介绍</a>
|
| 64 |
-
|
| 65 |
|
| 66 |
|
| 67 |
## 期望模型使用方式及适用范围
|
|
|
|
| 20 |
ChatYuan-large-v2 is a functional dialogue language model that supports bilingual Chinese and English.
|
| 21 |
ChatYuan-large-v2 uses the same technical solution as the v1 version, and has been optimized in terms of instruct-tuning, human feedback reinforcement learning and chain-of-thought.
|
| 22 |
|
| 23 |
+
<a href='https://huggingface.co/spaces/ClueAI/ChatYuan-large-v2' target="__blank">在线Demo huggingface space </a> |
|
| 24 |
+
<a href='https://www.clueai.cn' target="__blank">使用API(large版)</a> |
|
| 25 |
+
<a href='https://github.com/clue-ai/ChatYuan' target="__blank">Github项目地址</a> |
|
| 26 |
+
<a href='https://colab.research.google.com/drive/1ZcLIJuemiojigrfjbsDMBWrX7JqXZX6I?usp=sharing' target="__blank">Colab在线试用</a> |
|
| 27 |
+
<a href='https://mp.weixin.qq.com/s/-axa6XcjGl_Koeq_OrDq8w' target="__blank">文章介绍</a>
|
| 28 |
+
|
| 29 |
+
|
| 30 |
+
ChatYuan-large-v2是ChatYuan系列中以轻量化实现高质量效果的模型之一，用户可以在消费级显卡(6G)、 PC甚至手机上进行推理（INT4 最低只需 400M ）。
|
| 31 |
|
| 32 |
在chatyuan-large-v1的原有功能的基础上，我们给模型进行了如下优化：
|
| 33 |
- 增强了基础能力。原有上下文问答、创意性写作能力明显提升。
|
|
|
|
| 63 |
|
| 64 |
<a href='https://www.cluebenchmarks.com/clueai.html'>PromptCLUE-large</a>在1000亿token中文语料上预训练，累计学习1.5万亿中文token，并且在数百种任务上进行Prompt任务式训练。针对理解类任务，如分类、情感分析、抽取等，可以自定义标签体系；针对多种生成任务，可以进行采样自由生成。
|
| 65 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 66 |
|
| 67 |
|
| 68 |
## 期望模型使用方式及适用范围
|