Upload 6 files

.gitignore

@@ -0,0 +1,2 @@
+.venv/
+.env

app.py

@@ -0,0 +1,83 @@
+import os
+import requests 
+requests.adapters.DEFAULT_TIMEOUT = 60
+
+from dotenv import load_dotenv, find_dotenv
+_ = load_dotenv(find_dotenv()) # read local .env file
+hf_api_key = os.environ['HF_API_KEY']
+
+# Helper function
+import requests, json
+from text_generation import Client
+
+
+#FalcomLM-instruct endpoint on the text_generation library
+URL = "https://api-inference.huggingface.co/models/HuggingFaceH4/zephyr-7b-beta"
+client = Client(URL, timeout=120)
+
+#Back to Lesson 2, time flies!
+import gradio as gr
+def generate(input, slider):
+    output = client.generate(input, max_new_tokens=slider).generated_text
+    return output
+
+def format_chat_prompt(message, chat_history, instruction):
+    prompt = f"System:{instruction}"
+    for turn in chat_history:
+        user_message, bot_message = turn
+        prompt = f"{prompt}\nUser: {user_message}\nAssistant: {bot_message}"
+    prompt = f"{prompt}\nUser: {message}\nAssistant:"
+    return prompt
+
+def respond(message, chat_history, instruction, temperature=0.7):
+    prompt = format_chat_prompt(message, chat_history, instruction)
+    chat_history = chat_history + [[message, ""]]
+    stream = client.generate_stream(prompt,
+                                      max_new_tokens=1024,
+                                      stop_sequences=["\nUser:", "<|endoftext|>"],
+                                      temperature=temperature)
+                                      #stop_sequences to not generate the user answer
+    acc_text = ""
+    #Streaming the tokens
+    for idx, response in enumerate(stream):
+            text_token = response.token.text
+
+            if response.details:
+                return
+
+            if idx == 0 and text_token.startswith(" "):
+                text_token = text_token[1:]
+
+            acc_text += text_token
+            last_turn = list(chat_history.pop(-1))
+            last_turn[-1] += acc_text
+            chat_history = chat_history + [last_turn]
+            yield "", chat_history
+            acc_text = ""
+
+
+
+def loadGUI():
+    with gr.Blocks() as demo:
+        chatbot = gr.Chatbot(height=240) #just to fit the notebook
+        msg = gr.Textbox(label="Prompt")
+        with gr.Accordion(label="Advanced options",open=False):
+            system = gr.Textbox(label="System message", lines=2, value="A conversation between a user and an LLM-based AI assistant. The assistant gives helpful and honest answers.")
+            temperature = gr.Slider(label="temperature", minimum=0.1, maximum=1, value=0.7, step=0.1)
+        btn = gr.Button("Submit")
+        clear = gr.ClearButton(components=[msg, chatbot], value="Clear console")
+
+        btn.click(respond, inputs=[msg, chatbot, system], outputs=[msg, chatbot])
+        msg.submit(respond, inputs=[msg, chatbot, system], outputs=[msg, chatbot]) #Press enter to submit
+
+        gr.close_all()
+        demo.queue().launch(share=True) 
+    
+     
+def main():
+     loadGUI()
+     
+     
+if __name__ == "__main__":
+     main()
+          

requirements.txt

@@ -0,0 +1,76 @@
+accelerate==0.25.0
+aiofiles==23.2.1
+altair==5.2.0
+annotated-types==0.6.0
+anyio==3.7.1
+attrs==23.1.0
+certifi==2023.11.17
+charset-normalizer==3.3.2
+click==8.1.7
+colorama==0.4.6
+contourpy==1.2.0
+cycler==0.12.1
+fastapi==0.104.1
+ffmpy==0.3.1
+filelock==3.13.1
+fonttools==4.46.0
+fsspec==2023.12.1
+gradio==4.8.0
+gradio_client==0.7.1
+h11==0.14.0
+httpcore==1.0.2
+httpx==0.25.2
+huggingface-hub==0.19.4
+idna==3.6
+importlib-resources==6.1.1
+Jinja2==3.1.2
+jsonschema==4.20.0
+jsonschema-specifications==2023.11.2
+kiwisolver==1.4.5
+markdown-it-py==3.0.0
+MarkupSafe==2.1.3
+matplotlib==3.8.2
+mdurl==0.1.2
+mpmath==1.3.0
+networkx==3.2.1
+numpy==1.26.2
+orjson==3.9.10
+packaging==23.2
+pandas==2.1.4
+Pillow==10.1.0
+psutil==5.9.6
+pydantic==2.5.2
+pydantic_core==2.14.5
+pydub==0.25.1
+Pygments==2.17.2
+pyparsing==3.1.1
+python-dateutil==2.8.2
+python-dotenv==1.0.0
+python-multipart==0.0.6
+pytz==2023.3.post1
+PyYAML==6.0.1
+referencing==0.32.0
+regex==2023.10.3
+requests==2.31.0
+rich==13.7.0
+rpds-py==0.13.2
+safetensors==0.4.1
+semantic-version==2.10.0
+shellingham==1.5.4
+six==1.16.0
+sniffio==1.3.0
+starlette==0.27.0
+sympy==1.12
+tokenizers==0.15.0
+tomlkit==0.12.0
+toolz==0.12.0
+torch==2.1.1
+tqdm==4.66.1
+transformers==4.35.2
+typer==0.9.0
+typing_extensions==4.8.0
+tzdata==2023.3
+urllib3==2.1.0
+uvicorn==0.24.0.post1
+websockets==11.0.3
+text-generation==0.6.1