@raghavbj24 In parallel, if you do not mind: could you please rerun your experiment using this base model: alexsherstinsky/Mistral-7B-v0.1-sharded -- and let me know here what you see for the merged model size (and please also tell me the location where it will be saved). Thank you very much for your collaboration.
4条答案
按热度按时间ego6inou1#
你好,raghavbj24 -感谢你提交这个问题!我有一个问题想问你:我看到你的
base_model
是/home/ubuntu/llama-2-7b-hf_for_merge
。如果你尝试使用https://huggingface.co/meta-llama/Llama-2-7b-hf
中的meta-llama/Llama-2-7b-hf
,是否会发生相同的"小尺寸"现象?请让我知道。谢谢。ki0zmccv2#
你好,@alexsherstinsky。根据你的建议,我尝试了huggingface的base模型
meta-llama/Llama-2-7b-hf
,但是没有发现任何差异,而且保存的模型大小非常小。x3naxklr3#
raghavbj24,请问您的模型保存在HuggingFace的哪个位置?能否让我以"只读"权限访问它?我将在接下来的几天里深入研究。谢谢。
myss37ts4#
@raghavbj24 In parallel, if you do not mind: could you please rerun your experiment using this base model:
alexsherstinsky/Mistral-7B-v0.1-sharded
-- and let me know here what you see for the merged model size (and please also tell me the location where it will be saved). Thank you very much for your collaboration.