bot

config.py

@@ -68,8 +68,8 @@ MAX_RECENT_HISTORY_MESSAGES = int(os.getenv("MAX_RECENT_HISTORY_MESSAGES", 6))
 # "local" -> Mistral-7B-Instruct-v0.2 via transformers/bitsandbytes
 # "groq"  -> future Groq-hosted provider
 # "openai"-> future OpenAI provider
-LLM_PROVIDER = os.getenv("LLM_PROVIDER", "local")
-# LLM_PROVIDER = os.getenv("LLM_PROVIDER", "groq")
+# LLM_PROVIDER = os.getenv("LLM_PROVIDER", "local")
+LLM_PROVIDER = os.getenv("LLM_PROVIDER", "groq")
 
 LOCAL_MODEL_NAME = os.getenv("LOCAL_MODEL_NAME", "mistralai/Mistral-7B-Instruct-v0.2")
 LOCAL_MODEL_MAX_NEW_TOKENS = int(os.getenv("LOCAL_MODEL_MAX_NEW_TOKENS", 512))

llm/local_provider.py

@@ -12,11 +12,10 @@ Requires: transformers, bitsandbytes, torch, accelerate (see requirements.txt)
 import config
 from llm.provider import LLMProvider
 from logs.logger import get_logger
-import spaces 
 
 logger = get_logger(__name__)
 
-@spaces.GPU
+
 class LocalMistralProvider(LLMProvider):
     def __init__(self):
         self._model = None