Upload 5 files

app.py

@@ -0,0 +1,27 @@
+import gradio as gr
+from pathlib import Path
+
+from hf_chatinterface import demo as hf_chatinterface
+from hf_stream_demo import demo as hf_stream
+from transformers_local import demo as transformers_local
+
+
+with gr.Blocks() as demo:
+    with gr.Tabs():
+        for file_name, sub_demo, name in [
+            ("hf_chatinterface", hf_chatinterface, "ChatInterface with HF Inference API 🤗"),
+            ("transformers_local", transformers_local, "ChatInterface with Transformers Local 🤗"),
+            ("hf_stream_demo", hf_stream, "Blocks with HF Inference API 🤗"),
+        ]:
+            with gr.Tab(name):
+                with gr.Tabs():
+                    with gr.Tab("Demo"):
+                        sub_demo.render()
+                    with gr.Tab("Code"):
+                        gr.Code(
+                            value=Path(f"{file_name}.py").read_text(), language="python"
+                        )
+
+
+if __name__ == "__main__":
+    demo.launch()

hf_chatinterface.py

@@ -0,0 +1,49 @@
+from huggingface_hub import InferenceClient
+import gradio as gr
+
+client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
+
+
+def respond(
+    message,
+    history: list[tuple[str, str]],
+    system_message,
+    max_tokens,
+    temperature,
+    top_p,
+):
+    messages = [{"role": "system", "content": system_message}]
+
+    for val in history:
+        if val[0]:
+            messages.append({"role": "user", "content": val[0]})
+        if val[1]:
+            messages.append({"role": "assistant", "content": val[1]})
+
+    messages.append({"role": "user", "content": message})
+
+    response = ""
+
+    for message in client.chat_completion(
+        messages,
+        max_tokens=max_tokens,
+        stream=True,
+        temperature=temperature,
+        top_p=top_p,
+    ):
+        token = message.choices[0].delta.content
+
+        response += token
+        yield response
+
+
+demo = gr.ChatInterface(
+    respond,
+    chatbot=gr.Chatbot(height=400),
+    additional_inputs=[
+        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
+    ],
+)
+
+if __name__ == "__main__":
+    demo.launch()

hf_stream_demo.py

@@ -0,0 +1,51 @@
+from huggingface_hub import InferenceClient
+from gradio_agentchatbot import AgentChatbot
+import gradio as gr
+
+"""
+For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
+"""
+client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
+
+
+def respond(
+    prompt: str,
+    history,
+):
+    messages = [{"role": "system", "content": "You are a friendly chatbot"}]
+
+    for val in history:
+        if val[0]:
+            messages.append({"role": "user", "content": val[0]})
+        if val[1]:
+            messages.append({"role": "assistant", "content": val[1]})
+
+    yield messages
+    messages.append({"role": "user", "content": prompt})
+    history.append([prompt, None])
+    
+    response = ""
+    for message in client.chat_completion(
+        messages,
+        stream=True,
+    ):
+        response += message.choices[0].delta.content or ""
+        history[-1][1] = response
+        yield history
+
+
+with gr.Blocks() as demo:
+    gr.Markdown("# Chat with Hugging Face Zephyr 7b 🤗")
+    chatbot = AgentChatbot(
+        label="Agent",
+        avatar_images=(
+            None,
+            "https://em-content.zobj.net/source/twitter/376/hugging-face_1f917.png",
+        ),
+    )
+    prompt = gr.Textbox(lines=1, label="Chat Message")
+    prompt.submit(respond, [prompt, chatbot], [chatbot])
+
+
+if __name__ == "__main__":
+    demo.launch()

requirements.txt

@@ -0,0 +1 @@
+transformers

transformers_local.py

@@ -0,0 +1,77 @@
+import gradio as gr
+from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
+from threading import Thread
+import spaces
+
+tokenizer = AutoTokenizer.from_pretrained("mistralai/Mistral-7B-Instruct-v0.3")
+model = AutoModelForCausalLM.from_pretrained("mistralai/Mistral-7B-Instruct-v0.3", device_map="auto")
+terminators = [
+    tokenizer.eos_token_id,
+    tokenizer.convert_tokens_to_ids("<|eot_id|>")
+]
+
+
+@spaces.GPU(duration=120)
+def chat_mistral7b_v0dot3(message: str, 
+              history: list, 
+              temperature: float, 
+              max_new_tokens: int
+             ) -> str:
+
+    conversation = []
+    for user, assistant in history:
+        conversation.extend([{"role": "user", "content": user}, {"role": "assistant", "content": assistant}])
+    conversation.append({"role": "user", "content": message})
+
+    input_ids = tokenizer.apply_chat_template(conversation, return_tensors="pt").to(model.device)
+    
+    streamer = TextIteratorStreamer(tokenizer, timeout=10.0, skip_prompt=True, skip_special_tokens=True)
+
+    generate_kwargs = dict(
+        input_ids= input_ids,
+        streamer=streamer,
+        max_new_tokens=max_new_tokens,
+        do_sample=True,
+        temperature=temperature,
+        eos_token_id=terminators,
+    )
+    # This will enforce greedy generation (do_sample=False) when the temperature is passed 0, avoiding the crash.             
+    if temperature == 0:
+        generate_kwargs['do_sample'] = False
+        
+    t = Thread(target=model.generate, kwargs=generate_kwargs)
+    t.start()
+
+    outputs = []
+    for text in streamer:
+        outputs.append(text)
+        #print(outputs)
+        yield "".join(outputs)
+        
+
+# Gradio block
+with gr.Blocks() as demo:
+    gr.Markdown("# ChatInterface with Mistral and Transformers 🤗")
+    gr.ChatInterface(
+        fn=chat_mistral7b_v0dot3,
+        fill_height=True,
+        additional_inputs_accordion=gr.Accordion(label="⚙️ Parameters", open=False, render=False),
+        additional_inputs=[
+            gr.Slider(minimum=0,
+                      maximum=1, 
+                      step=0.1,
+                      value=0.95, 
+                      label="Temperature", 
+                      render=False),
+            gr.Slider(minimum=128, 
+                      maximum=4096,
+                      step=1,
+                      value=512, 
+                      label="Max new tokens", 
+                      render=False ),
+            ],
+    )
+    
+  
+if __name__ == "__main__":
+    demo.launch()