-
### System Info
Copy-and-paste the text below in your GitHub issue and FILL OUT the two last points.
- `transformers` version: 4.44.0
- Platform: Linux-5.4.0-165-generic-x86_64-with-glibc2.31
…
-
很奇怪的问题是,在8*A100(80G)上无论我如何设置max-seq,从16000降到200,始终都会OOM。
如下是我的命令和配置:
NPROC_PER_NODE=8 nohup xtuner train qwen1_5_32b_chat --deepspeed deepspeed_zero3 > instruct.out 2>&1 &
#################…
wgs97 updated
3 months ago
-
Do we want bootstrapped estimates of uncertainty for the different metrics? If so, how do we want to compute it for the different curves ?
-
We want to try out the averaging algorithm used by the CVPR paper **Revisiting Rotation Averaging: Uncertainties and Robust Losses** and benchmark the results on our datasets.
This was also sugges…
-
## Adding a Dataset
- **Name:** GLUECoS
- **Description:** a Microsoft Benchmark to evaluate code-switching for only two language pairs but a variety of tasks
- **Paper:** https://aclanthology.org/…
-
There's pretty interesting paper [1] which among other things introduces
SELECT-oriented benchmark w/ IMBD-based dataset [2].
Let's onboard it.
[1] - https://github.com/gregrahn/join-order-benc…
-
Hello,
It seems like there is an alternative download page of pubtables-1m on huggingface. Did you applied the canonicalization and consistency adjustment mentioned in the paper, "aligning benchmar…
-
Hi, I have been trying to run the method on the datasets in the benchmark (https://github.com/JieyuZ2/wrench). It seems the method doesn't support datasets with abstention. Is this correct and is the…
-
### What is your issue?
In https://github.com/pydata/xarray/pull/7221 I showed that a major contributor the slowdown in inserting a new element was the cost associated with an internal only debugging…
-
This [paper](https://arxiv.org/pdf/2103.00854.pdf) introduces the Vyakarana benchmark and they have some syntactic and some sentence-level tasks:
- PoS Tagging
- Syntax Tree-depth Prediction
- Gram…