Update app.py

app.py

@@ -26,7 +26,8 @@ HF_TOKEN = os.environ.get("Inference_Calls", None)
 # from transformers import LlavaNextProcessor, LlavaNextForConditionalGeneration, TextIteratorStreamer
 # processor = LlavaNextProcessor.from_pretrained("llava-hf/llava-v1.6-mistral-7b-hf")
 # model = LlavaNextForConditionalGeneration.from_pretrained("llava-hf/llava-v1.6-mistral-7b-hf", torch_dtype=torch.float16, low_cpu_mem_usage=True)
-"""from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
+"""
+from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
 tokenizer = AutoTokenizer.from_pretrained(model_id, token=HF_TOKEN)
 model_id = "meta-llama/Meta-Llama-3-8B-Instruct"
 model = AutoModelForCausalLM.from_pretrained(
@@ -37,7 +38,8 @@ model = AutoModelForCausalLM.from_pretrained(
 terminators = [
     tokenizer.eos_token_id,
     tokenizer.convert_tokens_to_ids("<|eot_id|>")
-]"""
+]
+"""
 from huggingface_hub import InferenceClient
 model_id = "meta-llama/Meta-Llama-3-8B-Instruct"
 client = InferenceClient(model_id, api_key="HF_TOKEN")
@@ -86,7 +88,8 @@ def respond(
 
     messages.append({"role": "user", "content": message})
 
-"""input_ids = tokenizer.apply_chat_template(
+"""
+    input_ids = tokenizer.apply_chat_template(
         messages,
         add_generation_prompt=True,
         return_tensors="pt"
@@ -113,7 +116,8 @@ def respond(
     for text in streamer:
         outputs.append(text)
         #print(outputs)
-        yield "".join(outputs)"""
+        yield "".join(outputs)
+"""
 
     response = ""