wip

app.py

@@ -1,63 +1,25 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
-
-"""
-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(
-    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})
+from transformers import pipeline
+import torch
+import random
+import gradio as gr
 
-    response = ""
+model_path = "shuttie/mistral-7b-dadjokes-v2"
 
-    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
+generator = pipeline(
+            task="text-generation",
+            model=model_path,
+            torch_dtype=torch.bfloat16,
+            device_map="auto",
+        )
 
-        response += token
-        yield response
+prompt = "### Instruction:\nContinue a dad joke:\n\n### Input:\n{input}\n\n### Response:\n"
 
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
-)
+def make_response(message, history):
+    input = prompt.format(input=message)
+    generated = generator(input, return_full_text=False, max_new_tokens=64, num_return_sequences=1)
+    return generated[0]["generated_text"]
 
 
 if __name__ == "__main__":
-    demo.launch()
+    gr.ChatInterface(make_response).launch()

requirements.txt

@@ -1 +1,6 @@
-huggingface_hub==0.22.2
+gradio
+transformers
+torch
+accelerate
+sentencepiece
+protobuf