ItsMeDevRoland commited on
Commit
99d1dcd
·
verified ·
1 Parent(s): 56b07de

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +5 -7
app.py CHANGED
@@ -134,16 +134,14 @@ def respond(
134
 
135
  # Generate response
136
  try:
137
- response = ""
138
- for chunk in llm_model.generate(
139
  full_prompt,
140
- max_tokens=max_tokens,
141
  stop=["User:", "\n"], # Stop on new user input
142
  temperature=temperature,
143
- top_p=top_p,
144
- stream=True
145
- ):
146
- response += chunk
147
 
148
  return response
149
  except Exception as e:
 
134
 
135
  # Generate response
136
  try:
137
+ # Use the correct method signature for llama-cpp-python
138
+ response = llm_model(
139
  full_prompt,
140
+ max_new_tokens=max_tokens, # Changed from max_tokens to max_new_tokens
141
  stop=["User:", "\n"], # Stop on new user input
142
  temperature=temperature,
143
+ top_p=top_p
144
+ )['choices'][0]['text']
 
 
145
 
146
  return response
147
  except Exception as e: