AGI-Edgerunners LLM-Adapters issues

AGI-Edgerunners / LLM-Adapters

Code for our EMNLP 2023 Paper: "LLM-Adapters: An Adapter Family for Parameter-Efficient Fine-Tuning of Large Language Models"

https://arxiv.org/abs/2304.01933

Apache License 2.0

1.08k stars 103 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

How to see the evalution results?

#72 gf457832386 opened 1 month ago
0
Baseline evaluation

#71 Yonghao-Tan opened 2 months ago
0
Questions about the accuracy of eight commonsense reasoning datasets vs the Llama paper

#70 Yonghao-Tan opened 2 months ago
2
Question on the source of commonsense_15k

#69 clarenceluo78 opened 6 months ago
3
Can not find BottleneckConfig

#68 1148514800 opened 6 months ago
2
Training loss goes to 0 and eval loss goes to nan

#67 ZeguanXiao opened 6 months ago
5
Question about datasets variants

#66 ZeguanXiao opened 6 months ago
1
about loss

#65 haoyuwangwhy opened 6 months ago
1
Reproduce the commense results on Boolq

#64 Zhenyu001225 opened 7 months ago
23
Gibberish output

#63 Aradhye2002 closed 7 months ago
6
Full-Parameter Fine-Tuning on commonsense

#62 lucasliunju closed 6 months ago
16
Possible Bug In Handling Batch Size During Common Sense Evaluation

#61 mchorton opened 7 months ago
1
AttributeError: 'tuple' object has no attribute 'update'

#60 YananLi18 opened 7 months ago
5
Is there any way to evaluate models without any adapters?

#59 smkim0220 closed 8 months ago
0
Question about the reproducation of the results in the math_10k

#58 zeyuliu1037 opened 8 months ago
13
FT with bottleneck : cannot perform fine-tuning on purely quantized models

#57 Lao-yy opened 8 months ago
2
p-tuning in finetune.py?

#56 smkim0220 opened 9 months ago
0
Can't fine tune/train when the model is loaded in 8bit

#55 Wonigox closed 9 months ago
7
请问为如何两次加载不同的微调后生成的lora权重？

#54 jinlong7790 opened 9 months ago
1
How does chatglm support p-tuning in code?

#53 lyt719 opened 11 months ago
0
mawps dataset

#52 LYH-YF closed 11 months ago
0
update math14k and math7k

#51 LYH-YF closed 11 months ago
0
How to Reproduce BLOOMz-7b and GPT-j-6 results?

#50 Ocean-627 closed 10 months ago
1
Guidance Request for Reproducing OpenbookQA Dataset Results

#49 FairyFali opened 12 months ago
1
weird evaluation results: 0% accuracy

#48 wum67 closed 10 months ago
1
ValueError: The version of PEFT you are using is not compatible, please use a version that is greater than 0.5.0

#47 nbasyl opened 1 year ago
6
Upload evaluation outputs and adapters

#46 mkeoliya opened 1 year ago
3
Details on provided peft

#45 aksh555 closed 1 year ago
2
how to download the dataset

#44 ello0211 opened 1 year ago
1
Question regarding the source of math_10k.json

#43 HuangOwen opened 1 year ago
10
Update README.md

#42 demoleiwang closed 8 months ago
0
Training reproduce

#41 ChaoGaoUCR opened 1 year ago
2
Questions about evaluate time

#40 Yuan0320 opened 1 year ago
4
Peft version problem

#39 marlin-codes closed 1 year ago
2
Couldn't get the same accuracy with eight commonsense reasoning datasets.

#38 ello0211 opened 1 year ago
7
Problems I came across when I try to reprocude the results

#37 ChaoGaoUCR opened 1 year ago
3
Errors when I run generation

#36 ChaoGaoUCR opened 1 year ago
5
AdapterH, AdapterP code

#35 ChaoGaoUCR opened 1 year ago
2
Eval without Tuning/Using OPT-1.3B

#34 ChaoGaoUCR opened 1 year ago
2
[Bug] Lora finetuning memory keeps rising until it is Out Of Memory

#33 angelOnly opened 1 year ago
1
How to evaluate a model fine-tuned with prefix?

#32 heart-and-soul opened 1 year ago
6
Add commonsense reasoning task

#31 HZQ950419 closed 1 year ago
0
finetune accuracy is much higher than what is in the README table

#30 CrazyElements opened 1 year ago
4
Could you give me an example to fintuning the Chatglm with adapter bottleneck please?

#29 zhaojunGUO opened 1 year ago
0
how to tune chatglm6b with dialogue dataset?

#28 zhaojunGUO opened 1 year ago
0
How to use llama-13B or bigger models?

#27 feiyuehchen opened 1 year ago
1
Couldn't get the same accuracy as the table (7B model LoRA)

#26 ywen666 closed 1 year ago
4
any code to merge the adapter weight with the original base model?

#25 sohuren opened 1 year ago
1
How to overwrite the Adapter

#24 YuChen17Heaven opened 1 year ago
3
upload running commands for math reasoning

#22 HZQ950419 closed 1 year ago
0