From d380db250c666805dd443d53987868b5ae4b8c7d Mon Sep 17 00:00:00 2001
From: Elvin-Ma <elvin0505@163.com>
Date: Sun, 2 Jul 2023 15:15:20 +0800
Subject: [PATCH] add chatgpt

---
 .../flask_deploy/{READEME.md => README.md}    |  0
 14-model_learning/chatGLM/README.md           | 26 +++++++++++++++++++
 2 files changed, 26 insertions(+)
 rename 13-model_deploy_guide/flask_deploy/{READEME.md => README.md} (100%)
 create mode 100644 14-model_learning/chatGLM/README.md

diff --git a/13-model_deploy_guide/flask_deploy/READEME.md b/13-model_deploy_guide/flask_deploy/README.md
similarity index 100%
rename from 13-model_deploy_guide/flask_deploy/READEME.md
rename to 13-model_deploy_guide/flask_deploy/README.md
diff --git a/14-model_learning/chatGLM/README.md b/14-model_learning/chatGLM/README.md
new file mode 100644
index 0000000..8cb3264
--- /dev/null
+++ b/14-model_learning/chatGLM/README.md
@@ -0,0 +1,26 @@
+# 聊天机器人
+```shell
+pip install protobuf transformers==4.27.1 cpm_kernels
+```
+## coding
+```python
+from transformers import AutoTokenizer, AutoModel
+
+tokenizer = AutoTokenizer.from_pretrained("./chatglm-6b-int4", trust_remote_code=True)
+model = AutoModel.from_pretrained("./chatglm-6b-int4", trust_remote_code=True).half().cuda()
+response, history = model.chat(tokenizer, "你好", history=[])
+print(response)
+
+# 你好👋!我是人工智能助手 ChatGLM-6B,很高兴见到你,欢迎问我任何问题。
+
+response, history = model.chat(tokenizer, "晚上睡不着应该怎么办", history=history)
+print(response)
+```
+
+## pretrained model
+- [链接](https://pan.baidu.com/s/1VPRGReHfnnqe_ULKjquoaQ?pwd=oaae)
+- 提取码：oaae 
+
+# 参考资料
+[参考资料2](https://huggingface.co/THUDM/chatglm-6b-int4)
+[参考资料](https://github.com/wenda-LLM/wenda/tree/main)
\ No newline at end of file