Update generate function

app.py

@@ -1,5 +1,6 @@
 #!/usr/bin/env python
 import os
+from threading import Thread
 from typing import Iterator
 
 import gradio as gr
@@ -14,14 +15,9 @@ DEFAULT_MAX_NEW_TOKENS = 1024
 MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "8192"))
 
 if torch.cuda.is_available():
-    # model_id = "meta-llama/Meta-Llama-3.1-8B-Instruct"
-    # model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16, device_map="auto")
-    # tokenizer = AutoTokenizer.from_pretrained(model_id)
-    pass
-
-style = None
-
-AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
+    model_id = "meta-llama/Meta-Llama-3.1-8B-Instruct"
+    model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16, device_map="auto")
+    tokenizer = AutoTokenizer.from_pretrained(model_id)
 
 
 @spaces.GPU
@@ -34,39 +30,36 @@ def generate(
     top_k: int = 40,
     repetition_penalty: float = 1.2,
 ) -> Iterator[str]:
-    # conversation = []
-    # for user, assistant in chat_history:
-    #     conversation.extend([{"role": "user", "content": user}, {"role": "assistant", "content": assistant}])
-    # conversation.append({"role": "user", "content": message})
-
-    # input_ids = tokenizer.apply_chat_template(conversation, add_generation_prompt=True, 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)
-
-    # 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()
-
-    # outputs = []
-    # for text in streamer:
-    #     outputs.append(text)
-    #     yield "".join(outputs)
-
-    for char in "help":
-        yield "help"
+    conversation = []
+    for user, assistant in chat_history:
+        conversation.extend([{"role": "user", "content": user}, {"role": "assistant", "content": assistant}])
+    conversation.append({"role": "user", "content": message})
+
+    input_ids = tokenizer.apply_chat_template(conversation, add_generation_prompt=True, 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)
+
+    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()
+
+    outputs = []
+    for text in streamer:
+        outputs.append(text)
+        yield "".join(outputs)
 
 
 chat_interface = ChatInterface(