Closed marvin-Yu closed 6 months ago
The current Qwen-72B model conversion process consumes approximately 282GB of memory, which far exceeds the configuration of the machines currently used by the client. This PR modify the conversion method to reduce memory usage to around 20~30GB.
The current Qwen-72B model conversion process consumes approximately 282GB of memory, which far exceeds the configuration of the machines currently used by the client. This PR modify the conversion method to reduce memory usage to around 20~30GB.