testing open model

app.py

@@ -1,73 +1,31 @@
-import gradio as gr
 from llama_cpp import Llama
-from huggingface_hub import hf_hub_download
-
-# Download the file from Hugging Face
-model_path = hf_hub_download(repo_id="rcarioniporras/model", filename="unsloth.Q4_K_M.gguf")
-
-# Load the model using llama_cpp
-llm = Llama(model_path=model_path, verbose=False)
-
-
-# """
-# 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
-# """
-# llm = Llama.from_pretrained(
-#     repo_id="rcarioniporras/model",
-#     filename="*Q4_K_M.gguf",
-#     verbose=False
-# )
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
+import gradio as gr
 
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+llm = Llama.from_pretrained(
+	repo_id="Robzy/Llama-3.2-1B-Instruct-Finetuned-q4_k_m",
+	filename="unsloth.Q4_K_M.gguf",
+)
 
+def predict(message, history):
+    messages = [{"role": "system", "content": "You are a helpful assistant."}]
+    for user_message, bot_message in history:
+        if user_message:
+            messages.append({"role": "user", "content": user_message})
+        if bot_message:
+            messages.append({"role": "assistant", "content": bot_message})
     messages.append({"role": "user", "content": message})
-
+    
     response = ""
-    for message in llm.chat_completion(
-        messages,
-        max_tokens=max_tokens,
+    for chunk in llm.create_chat_completion(
         stream=True,
-        temperature=temperature,
-        top_p=top_p,
+        messages=messages,
     ):
-        token = message.choices[0].delta.content
-
-        response += token
+        part = chunk["choices"][0]["delta"].get("content", None)
+        if part:
+            response += part
         yield response
 
-"""
-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)",
-        ),
-    ],
-)
-
+demo = gr.ChatInterface(predict)
 
 if __name__ == "__main__":
     demo.launch()