Create app.py

app.py

@@ -0,0 +1,59 @@
+!pip install gradio
+!pip install transformers
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer, StoppingCriteria, StoppingCriteriaList, TextIteratorStreamer
+from threading import Thread
+tokenizer = AutoTokenizer.from_pretrained("togethercomputer/RedPajama-INCITE-Chat-3B-v1")
+model = AutoModelForCausalLM.from_pretrained("togethercomputer/RedPajama-INCITE-Chat-3B-v1", torch_dtype=torch.float16)
+model = model.to('cuda:0')
+class StopOnTokens(StoppingCriteria):
+    def __call__(self, input_ids: torch.LongTensor, scores: torch.FloatTensor, **kwargs) -> bool:
+        stop_ids = [29, 0]
+        for stop_id in stop_ids:
+            if input_ids[0][-1] == stop_id:
+                return True
+        return False
+def predict(message, history):
+
+    history_transformer_format = history + [[message, ""]]
+    stop = StopOnTokens()
+
+    messages = "".join(["".join(["\n<human>:"+item[0], "\n<bot>:"+item[1]])  #curr_system_message +
+                for item in history_transformer_format])
+
+    model_inputs = tokenizer([messages], return_tensors="pt").to("cuda")
+    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()
+
+    partial_message  = ""
+    for new_token in streamer:
+        if new_token != '<':
+            partial_message += new_token
+            yield partial_message
+
+import gradio as gr
+
+demo_llm = gr.ChatInterface(predict,
+                            chatbot=gr.Chatbot(height=500),
+                            textbox=gr.Textbox(placeholder="Ask me a yes or no question", container=False, scale=7),
+                            title="LLM Chatbot",
+                            description="Chat with LLM",
+                            theme="soft",
+                            examples=["Hello", "What are you?", "What is the meaning of life?"],
+                            cache_examples=True,
+                            retry_btn=None,
+                            undo_btn="Delete Previous",
+                            clear_btn="Clear")
+demo_llm.queue().launch()