Add Demos about ChatGLM

examples/ChatGLM2-Demo.py

@@ -0,0 +1,11 @@
+import os
+os.environ["PYTORCH_CUDA_ALLOC_CONF"] = "max_split_size_mb:32"
+
+import os
+from transformers import AutoTokenizer, AutoModel
+
+tokenizer = AutoTokenizer.from_pretrained("tunning/chatglm2-6b", trust_remote_code=True)
+model = AutoModel.from_pretrained("tunning/chatglm2-6b", trust_remote_code=True).cuda()
+model = model.eval()
+response, history = model.chat(tokenizer, "你好", history=[])
+print(response)

examples/DownloadChatGLM.py

@@ -0,0 +1,8 @@
+from transformers import AutoTokenizer, AutoModel
+tokenizer = AutoTokenizer.from_pretrained("THUDM/chatglm2-6b", trust_remote_code=True)
+model = AutoModel.from_pretrained("THUDM/chatglm2-6b", trust_remote_code=True, device='cuda')
+model = model.eval()
+response, history = model.chat(tokenizer, "你好", history=[])
+print(response)
+response, history = model.chat(tokenizer, "晚上睡不着应该怎么办", history=history)
+print(response)