| Model optimized for CPU deployment | |
| ================================== | |
| - Merged LoRA weights with base model | |
| - Converted to float32 precision | |
| - Optimized for CPU inference | |
| - Ready for function calling tasks | |
| Model optimized for CPU deployment | |
| ================================== | |
| - Merged LoRA weights with base model | |
| - Converted to float32 precision | |
| - Optimized for CPU inference | |
| - Ready for function calling tasks | |