We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
请问怎么将HuggingFace版本的Aquila2-7B模型和Aquila2-34B模型转化为Megatron模型,scripts中的convert_hf_to_megatron.py文件中需要ref_model_path,但是在项目中没有给出
The text was updated successfully, but these errors were encountered:
您好,已更新相关代码,请参考#38
转换脚本请参考:
export PYTHONPATH=/path/to/FlagScale/megatron # 34b python convert_hf_to_megatron.py -i {34b_hf_ckpt} -o {tgt_dir} -r ref_model/34b_ref_model --num-layers 60 --hidden-size 6144 --num-attention-heads 48 --data-type bf16 --group-query-attention --num-query-groups 8 # 7B python convert_hf_to_megatron.py -i {7b_hf_ckpt} -r ref_model/7b_ref_model -o {tgt_dir} --num-layers 32 --hidden-size 4096 --num-attention-heads 32 --data-type bf16
Sorry, something went wrong.
No branches or pull requests
请问怎么将HuggingFace版本的Aquila2-7B模型和Aquila2-34B模型转化为Megatron模型,scripts中的convert_hf_to_megatron.py文件中需要ref_model_path,但是在项目中没有给出
The text was updated successfully, but these errors were encountered: