added gradio for the model_card punjabi_gemma

app.py

@@ -1,64 +1,54 @@
 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})
-
-    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
-
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
+
+# Load your model and tokenizer
+model_name = "modelsmafia/punjabi_Gemma-2B"  # Replace with your model name
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16, device_map="auto")
+
+# Create a chat function
+def chat_with_model(message, history):
+    # Format the conversation history for your model
+    # This format may need adjustment based on your model's expected input format
+    prompt = ""
+    for h in history:
+        prompt += f"<start_of_turn>user\n{h[0]}<end_of_turn>\n"
+        prompt += f"<start_of_turn>model\n{h[1]}<end_of_turn>\n"
+    
+    prompt += f"<start_of_turn>user\n{message}<end_of_turn>\n<start_of_turn>model\n"
+    
+    # Generate response
+    inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+    outputs = model.generate(
+        inputs.input_ids,
+        max_new_tokens=512,
+        temperature=0.7,
+        top_p=0.9,
+        do_sample=True,
+        pad_token_id=tokenizer.eos_token_id
+    )
+    
+    response = tokenizer.decode(outputs[0][inputs.input_ids.shape[1]:], skip_special_tokens=True)
+    
+    # Remove any trailing "<end_of_turn>" if present
+    if "<end_of_turn>" in response:
+        response = response.split("<end_of_turn>")[0]
+    
+    return response
+
+# Create the Gradio interface
 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)",
-        ),
+    chat_with_model,
+    title="Chat with Punjabi Gemma 2B",
+    description="A bilingual chat model for English and Punjabi",
+    examples=[
+        ["ਸਤ ਸ੍ਰੀ ਅਕਾਲ, ਤੁਸੀਂ ਕਿਵੇਂ ਹੋ?"],
+        ["Tell me about Punjab in a few sentences."]
     ],
+    theme="soft"
 )
 
-
+# Launch the interface
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()

requirements.txt

@@ -1 +1,4 @@
-huggingface_hub==0.25.2
+huggingface_hub==0.25.2
+gradio
+transformers
+torch