modified the llama version

app.py

@@ -42,7 +42,7 @@ h1 {
 """
 
 # Load the tokenizer and model with quantization
-model_id = "meta-llama/Meta-Llama-3.1-8B-Instruct"
+model_id = "meta-llama/Meta-Llama-3-8B-Instruct"
 bnb_config = BitsAndBytesConfig(
     load_in_4bit=True,
     bnb_4bit_use_double_quant=True,
@@ -241,7 +241,7 @@ def chat_llama3_8b(message: str, history: list, temperature: float, max_new_toke
         responses = []
         count=0
         for chunk in chunks:
-            logger.info(f"Processing chunk {count+1}/{len(chunk)}")
+            logger.info(f"Processing chunk {count+1}/{len(chunks)}")
             response = generate_response_for_chunk(chunk, history, temperature, max_new_tokens)
             responses.append(response)
             count+=1

requirements.txt

@@ -2,5 +2,3 @@ accelerate
 transformers
 SentencePiece
 bitsandbytes
-torch
-transformers==4.43.1