Create app.py

app.py

@@ -0,0 +1,61 @@
+# Install Gradio for creating an interface
+!pip install -q gradio
+
+import gradio as gr
+import torch
+from transformers import AutoPeftModelForCausalLM, AutoTokenizer, StoppingCriteria, StoppingCriteriaList, TextIteratorStreamer
+from threading import Thread
+
+# Load the fine-tuned model and tokenizer
+new_model = "Ronal999/phi2_DPO"
+model = AutoPeftModelForCausalLM.from_pretrained(new_model,
+                                                 low_cpu_mem_usage=True,
+                                                 torch_dtype=torch.float16,
+                                                 load_in_4bit=True,)
+tokenizer = AutoTokenizer.from_pretrained(new_model)
+model = model.to('cuda:0')
+
+# Define stopping criteria
+class StopOnTokens(StoppingCriteria):
+    def __call__(self, input_ids: torch.LongTensor, scores: torch.FloatTensor, **kwargs) -> bool:
+        stop_ids = [29, 0]  # Token IDs to stop the generation
+        for stop_id in stop_ids:
+            if input_ids[0][-1] == stop_id:
+                return True
+        return False
+
+# Define the prediction function
+def predict(message, history):
+    # Transform history into the required format
+    history_transformer_format = history + [[message, ""]]
+    stop = StopOnTokens()
+
+    # Format messages for the model
+    messages = "".join(["".join(["\n<human>:"+item[0], "\n<bot>:"+item[1]]) for item in history_transformer_format])
+    model_inputs = tokenizer([messages], return_tensors="pt").to("cuda")
+
+    # Set up the streamer and generate responses
+    streamer = TextIteratorStreamer(tokenizer, timeout=10., skip_prompt=True, skip_special_tokens=True)
+    generate_kwargs = dict(
+        model_inputs,
+        streamer=streamer,
+        max_new_tokens=1024,
+        do_sample=True,
+        top_p=0.95,
+        top_k=1000,
+        temperature=1.0,
+        num_beams=1,
+        stopping_criteria=StoppingCriteriaList([stop])
+    )
+    t = Thread(target=model.generate, kwargs=generate_kwargs)
+    t.start()
+
+    # Yield partial messages as they are generated
+    partial_message = ""
+    for new_token in streamer:
+        if new_token != '<':
+            partial_message += new_token
+            yield partial_message
+
+# Launch Gradio Chat Interface
+gr.ChatInterface(predict).queue().launch(debug=True)