gsm8k-ScRel

gsm8k-ScRel copied to clipboard

if you have some plan to release data?

8

if you have some plan to release the training data?

ngc7292

The RFT data

4

Hi,after completing SFT and multipath reasoning, I have some doubts about the data under the data/rft path in your github code base. I would like to ask you how these...

ZIKEYUAN

Is majority voting(self-consistency) helpful for 70B llama2-sft model?

1

platoonpluto

the inference of OFA-Sys/gsm8k-rft-llama13b2-u13b has shape error: 13Bllama2的u13b版本推理时出现矩阵形状错误

8

There seems no people tried your 13b2-u13b version and I may be the first one. But I got 'RuntimeError: mat1 and mat2 shapes cannot be multiplied (111x5120 and 1x2560)' on...

Rem1L

About the collect_rejection_sampling.py

1

Where can we find the file or folder named ``./ckpt/gsm8k_sft_llama7b''?

jzh9830

请问repo中是否包含使用MuggleMath论文中提到的方法对GSM8K或者MATH进行数据增强的代码？

hlcle

Can I ask some questions? In the single_inference_7b_13b.py, there exists code in the implementation of `SupervisedDataset` class, ``` self.input_ids = data_dict["input_ids"] + data_dict["input_ids"][-100:] self.labels = data_dict["labels"] + data_dict["labels"][-100:] ``` I...

2004learner

ICL相关实现

1

请问ICL的相关实现要怎么做呢，没有在代码里面找到相关的信息

ywlq