Merge branch 'main' of https://github.com/zhaonx/LLaMA-Factory into dev

src/llmtuner/chat/chat_model.py

@@ -2,6 +2,7 @@ import asyncio
 from threading import Thread
 from typing import TYPE_CHECKING, Any, AsyncGenerator, Dict, Generator, List, Optional, Sequence
 
+from ..extras.misc import torch_gc
 from ..hparams import get_infer_args
 from .hf_engine import HuggingfaceEngine
 from .vllm_engine import VllmEngine
@@ -95,3 +96,45 @@ class ChatModel:
         **input_kwargs,
     ) -> List[float]:
         return await self.engine.get_scores(batch_input, **input_kwargs)
+
+
+def run_chat() -> None:
+    try:
+        import platform
+
+        if platform.system() != "Windows":
+            import readline  # noqa: F401
+    except ImportError:
+        print("Install `readline` for a better experience.")
+
+    chat_model = ChatModel()
+    messages = []
+    print("Welcome to the CLI application, use `clear` to remove the history, use `exit` to exit the application.")
+
+    while True:
+        try:
+            query = input("\nUser: ")
+        except UnicodeDecodeError:
+            print("Detected decoding error at the inputs, please set the terminal encoding to utf-8.")
+            continue
+        except Exception:
+            raise
+
+        if query.strip() == "exit":
+            break
+
+        if query.strip() == "clear":
+            messages = []
+            torch_gc()
+            print("History has been removed.")
+            continue
+
+        messages.append({"role": "user", "content": query})
+        print("Assistant: ", end="", flush=True)
+
+        response = ""
+        for new_text in chat_model.stream_chat(messages):
+            print(new_text, end="", flush=True)
+            response += new_text
+        print()
+        messages.append({"role": "assistant", "content": response})