Zephyruswind

Results 3 issues of Zephyruswind

Could the project support the lastest model Gemma which has much higher performance than LLAMA2?

When the quantity of documents is large, the below errors accur: results = cur.execute(sql, params).fetchall() sqlite3.OperationalError: too many SQL variables Anyone who has encounters this issue? LOGS: (localGPT) PS D:\projects_llm\lgpt>...

How could we add the streaming support to enhance the output effect?