dev - magic

app.py

@@ -64,14 +64,6 @@ MAX_MAX_NEW_TOKENS = 2048
 DEFAULT_MAX_NEW_TOKENS = 1024
 MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "4096"))
 
-
-
-
-if torch.cuda.is_available():
-    model_id = "mistralai/Mistral-7B-Instruct-v0.1"
-    model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16, device_map="auto")
-    tokenizer = AutoTokenizer.from_pretrained(model_id)
-
 # we need to make sure we only run one thread or we probably run out of ram
 def generate(
     message: str,
@@ -87,34 +79,17 @@ def generate(
         conversation.extend([{"role": "user", "content": user}, {"role": "assistant", "content": assistant}])
     conversation.append({"role": "user", "content": message})
 
-    input_ids = tokenizer.apply_chat_template(conversation, return_tensors="pt")
-    if input_ids.shape[1] > MAX_INPUT_TOKEN_LENGTH:
-        input_ids = input_ids[:, -MAX_INPUT_TOKEN_LENGTH:]
-        gr.Warning(f"Trimmed input from conversation as it was longer than {MAX_INPUT_TOKEN_LENGTH} tokens.")
-    input_ids = input_ids.to(model.device)
-
-    llm.generate('test')
-    streamer = TextIteratorStreamer(tokenizer, timeout=10.0, skip_prompt=True, skip_special_tokens=True)
-    generate_kwargs = dict(
-        {"input_ids": input_ids},
-        streamer=streamer,
-        max_new_tokens=max_new_tokens,
-        do_sample=True,
-        top_p=top_p,
-        top_k=top_k,
-        temperature=temperature,
-        num_beams=1,
-        repetition_penalty=repetition_penalty,
-    )
-    t = Thread(target=model.generate, kwargs=generate_kwargs)
-    t.start()
+    # Use LLaMa to create chat completion
+    llm.create_chat_completion(conversation, stream=True)
+
+    # Initialize a TextIteratorStreamer
+    streamer = TextIteratorStreamer(llm, timeout=10.0, skip_prompt=True, skip_special_tokens=True)
 
     outputs = []
     for text in streamer:
         outputs.append(text)
         yield "".join(outputs)
 
-
 chat_interface = gr.ChatInterface(
     fn=generate,
     additional_inputs=[