-
# URL
- https://arxiv.org/abs/2409.12183
# Affiliations
- Zayne Sprague, N/A
- Fangcong Yin, N/A
- Juan Diego Rodriguez, N/A
- Dongwei Jiang, N/A
- Manya Wadhwa, N/A
- Prasann Singhal, N/A…
-
- [ ] Shortlist metrics
- [ ] Shortlist datasets - eval scripts available
- [ ] Write Evaluation script
-
Hi, thanks for sharing the datasets! I'm trying to train a flan model using t5 and other backbone models. However i'm not confident enough on how well I reproduced your results. Specifically I got muc…
-
### 🐛 Describe the bug
I'm trying to finetune Llama2-7B (to reproduce the experiments in a paper) using PEFT LoRA (0.124% of trainable params). However, this results in an out-of-memory (OOM) error o…
-
Because of the following LLM-Leaderboard measurements, I want to perform QLoRA DPO without previous QLoRA SFT:
```
alignment-handbook/zephyr-7b-dpo-qlora: +Average: 63.51; +ARC 63.65; +HSwag …
-
Hi,
Thanks for the interesting paper. I was wondering how to reproduce the scores reported in Table 1. I would appreciate it very much if you could provide the evaluation script. Many thanks.
-
**Details:**
**Here is your result :**
I used the following commands to reproduce the results of using the LLaMA 7B model on the Guanaco (OASST1) dataset:
**CUDA_VISIBLE_DEVICES=2 sh scripts/…
-
I want to load the local `mmlu` dataset, I have already load it from [hails/[mmlu_no_train](https://huggingface.co/datasets/hails/mmlu_no_train)，
, targets, reduction='batchmean')
Although the relative loss curve is the…
yynil updated
1 month ago