完成代码编写，尝试部署

Dockerfile

@@ -0,0 +1,16 @@
+# read the doc: https://huggingface.co/docs/hub/spaces-sdks-docker
+# you will also find guides on how best to write your Dockerfile
+
+FROM python:3.10
+
+WORKDIR /code
+
+COPY ./requirements.txt /code/requirements.txt
+
+RUN pip install --no-cache-dir --upgrade -r /code/requirements.txt
+
+COPY . .
+
+RUN wget https://huggingface.co/TheBloke/NeuralHermes-2.5-Mistral-7B-GGUF/resolve/main/neuralhermes-2.5-mistral-7b.Q5_K_M.gguf?download=true -O neuralhermes-2.5-mistral-7b.Q5_K_M.gguf
+
+CMD ["python", "app.py"]

app.py

@@ -0,0 +1,26 @@
+import gradio as gr
+from llama_cpp import Llama
+llm = Llama(model_path="./neuralhermes-2.5-mistral-7b.Q5_K_M.gguf",
+            chat_format="chatml")
+
+
+def chat_completion(messages, history, system_prompt):
+    messages = [{"role": "system", "content": system_prompt}]
+    messages.extend(history)
+    messages.append({"role": "user", "content": messages})
+    response = llm.create_chat_completion(
+        messages=messages,
+        stream=True
+    )
+    partial_message = ""
+    for chunk in response:
+        if len(chunk['choices'][0]['delta']) != 0:
+            partial_message = partial_message + \
+                chunk['choices'][0]['delta']['content']
+            yield partial_message
+
+
+gr.ChatInterface(chat_completion,
+                 additional_inputs=[gr.Textbox(
+                     "You are helpful AI.", label="System Prompt")]
+                 ).launch(server_name="0.0.0.0")

requirements.txt

@@ -0,0 +1,2 @@
+llama-cpp-python
+gradio