Update app.py

app.py

@@ -4,34 +4,50 @@ import torch
 
 
 title = "🦅Falcon 🗨️ChatBot"
-description ="Falcon-RW-1B is a 1B parameters causal decoder-only model built by TII and trained on 350B tokens of RefinedWeb."
+description = "Falcon-RW-1B is a 1B parameters causal decoder-only model built by TII and trained on 350B tokens of RefinedWeb."
 examples = [["How are you?"]]
 
 
 tokenizer = AutoTokenizer.from_pretrained("tiiuae/falcon-rw-1b")
-model = AutoModelForCausalLM.from_pretrained("tiiuae/falcon-rw-1b")
+model = AutoModelForCausalLM.from_pretrained(
+    "tiiuae/falcon-rw-1b",
+    trust_remote_code=True,
+    torch_dtype=torch.bfloat16,
+    trust_remote_code=True,
+    device_map="auto",
+)
+
 
 def predict(input, history=[]):
     # tokenize the new input sentence
-    new_user_input_ids = tokenizer.encode(input + tokenizer.eos_token, return_tensors='pt')
+    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()
+    # 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))
+    # 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,
-             title=title,
-             description=description,
-             examples=examples,
-             inputs=["text", "state"],
-             outputs=["chatbot", "state"],
-             theme='finlaymacklon/boxy_violet').launch()
+
+gr.Interface(
+    fn=predict,
+    title=title,
+    description=description,
+    examples=examples,
+    inputs=["text", "state"],
+    outputs=["chatbot", "state"],
+    theme="finlaymacklon/boxy_violet",
+).launch()