Swift now supports inference, training, deployment, and evaluation of Qwen1.5-110B.
#1
by
hu5enpai
- opened
https://github.com/modelscope/swift/
Inference: swift infer --model_id_or_path qwen/Qwen1.5-110B
Fine-tuning script: https://github.com/modelscope/swift/blob/main/examples/pytorch/llm/scripts/qwen1half_110b_chat/lora_ddp_ds/sft.sh
For more documentation, refer to https://github.com/modelscope/swift/tree/main/docs/source_en