codelion commited on
Commit
1e311d8
1 Parent(s): 3fd401e

Update main.py

Browse files
Files changed (1) hide show
  1. main.py +2 -2
main.py CHANGED
@@ -36,7 +36,7 @@ if 'chat_history' not in st.session_state:
36
  vector_store = SupabaseVectorStore(supabase, embeddings, query_name='match_documents', table_name="documents")
37
  memory = ConversationBufferMemory(memory_key="chat_history", input_key='question', output_key='answer', return_messages=True)
38
 
39
- model = "google/gemma-1.1-7b-it" #mistralai/Mixtral-8x7B-Instruct-v0.1
40
  temperature = 0.1
41
  max_tokens = 500
42
  stats = str(get_usage(supabase))
@@ -49,7 +49,7 @@ def response_generator(query):
49
  endpoint_url = ("https://api-inference.huggingface.co/models/"+ model)
50
  model_kwargs = {"temperature" : temperature,
51
  "max_new_tokens" : max_tokens,
52
- "repetition_penalty" : 1.1,
53
  "return_full_text" : False}
54
  hf = HuggingFaceEndpoint(
55
  endpoint_url=endpoint_url,
 
36
  vector_store = SupabaseVectorStore(supabase, embeddings, query_name='match_documents', table_name="documents")
37
  memory = ConversationBufferMemory(memory_key="chat_history", input_key='question', output_key='answer', return_messages=True)
38
 
39
+ model = "mistralai/Mixtral-8x7B-Instruct-v0.1"
40
  temperature = 0.1
41
  max_tokens = 500
42
  stats = str(get_usage(supabase))
 
49
  endpoint_url = ("https://api-inference.huggingface.co/models/"+ model)
50
  model_kwargs = {"temperature" : temperature,
51
  "max_new_tokens" : max_tokens,
52
+ # "repetition_penalty" : 1.1,
53
  "return_full_text" : False}
54
  hf = HuggingFaceEndpoint(
55
  endpoint_url=endpoint_url,