Update app.py

app.py

@@ -1,6 +1,7 @@
-from transformers import AutoModelForCausalLM, AutoTokenizer
 import gradio as gr
 import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer, StoppingCriteria, StoppingCriteriaList, TextIteratorStreamer
+from threading import Thread
 
 
 title = "🦅Falcon 🗨️ChatBot"
@@ -8,43 +9,54 @@ description = "Falcon-RW-1B is a 1B parameters causal decoder-only model built b
 examples = [["How are you?"]]
 
 
-tokenizer = AutoTokenizer.from_pretrained("tiiuae/falcon-rw-1b")
+tokenizer = AutoTokenizer.from_pretrained("tiiuae/falcon-rw-1b",torch_dtype=torch.float16)
 model = AutoModelForCausalLM.from_pretrained(
     "tiiuae/falcon-rw-1b",
     trust_remote_code=True,
+    torch_dtype=torch.float16
 )
 
 
-def predict(input, history=[]):
-    # tokenize the new input sentence
-    new_user_input_ids = tokenizer.encode(
-        input + tokenizer.eos_token, return_tensors="pt"
-    )
-
-    # append the new user input tokens to the chat history
-    bot_input_ids = torch.cat([torch.LongTensor(history), new_user_input_ids], dim=-1)
-
-    # generate a response
-    history = model.generate(
-        bot_input_ids, max_length=4000, pad_token_id=tokenizer.eos_token_id
-    ).tolist()
-
-    # convert the tokens to text, and then split the responses into lines
-    response = tokenizer.decode(history[0]).split("<|endoftext|>")
-    # print('decoded_response-->>'+str(response))
-    response = [
-        (response[i], response[i + 1]) for i in range(0, len(response) - 1, 2)
-    ]  # convert to tuples of list
-    # print('response-->>'+str(response))
-    return response, history
-
-
-gr.Interface(
-    fn=predict,
+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 
+            
+
+gr.ChatInterface(predictfn=predict,
     title=title,
     description=description,
-    examples=examples,
-    inputs=["text", "state"],
-    outputs=["chatbot", "state"],
-    theme="finlaymacklon/boxy_violet",
-).launch()
+    examples=examples).queue().launch()