Update app.py

app.py

@@ -28,7 +28,7 @@ import re
 list_llm = ["mistralai/Mistral-7B-Instruct-v0.2", "mistralai/Mixtral-8x7B-Instruct-v0.1", "mistralai/Mistral-7B-Instruct-v0.1", \
     "google/gemma-7b-it","google/gemma-2b-it", \
     "HuggingFaceH4/zephyr-7b-beta", "HuggingFaceH4/zephyr-7b-gemma-v0.1", \
-    "meta-llama/Meta-Llama-3-8B-Instruct","meta-llama/Meta-Llama-3.1-8B-Instruct", "microsoft/phi-2", \
+    "meta-llama/Meta-Llama-3-8B-Instruct","meta-llama/Meta-Llama-3.1-70B-Instruct", "microsoft/phi-2", \
     "TinyLlama/TinyLlama-1.1B-Chat-v1.0", "mosaicml/mpt-7b-instruct", "tiiuae/falcon-7b-instruct", \
     "google/flan-t5-xxl"
 ]
@@ -152,13 +152,13 @@ def initialize_llmchain(llm_model, temperature, max_tokens, top_k, vector_db, pr
             #huggingfacehub_api_token = huggingfacehub_api_token,
             top_k = top_k,
         )
-    elif llm_model == "meta-llama/Meta-Llama-3.1-8B-Instruct":
+    elif llm_model == "meta-llama/Meta-Llama-3.1-70B-Instruct":
         #raise gr.Error("Llama-2-7b-chat-hf model requires a Pro subscription...")
         llm = HuggingFaceEndpoint(
             repo_id=llm_model, 
             # model_kwargs={"temperature": temperature, "max_new_tokens": max_tokens, "top_k": top_k}
             temperature = temperature,
-            max_new_tokens = 450,
+            max_new_tokens = 500,
             #huggingfacehub_api_token = huggingfacehub_api_token,
             top_k = top_k,
         )