4AI LS-LLaMA issues - Githubissues

4AI / LS-LLaMA

A Simple but Powerful SOTA NER Model | Official Code For Label Supervised LLaMA Finetuning

https://arxiv.org/abs/2310.01208

MIT License

122 stars 19 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

Do you train only linear classification head or finetune the whole Llama model?

#22 ngthanhtin closed 3 weeks ago
2
process doubt for dataset

#21 misitetong opened 1 month ago
2
Can you provide multi GPU training script

#20 XYaoooo opened 2 months ago
0
Bitsandbytes quantization extension

#19 ferrazzipietro opened 2 months ago
3
Hi, what's the prompt for NER task?

#18 wmkai closed 3 months ago
5
RuntimeError with dtypes

#17 biirving opened 3 months ago
1
Ask pretrained weights

#16 nguyenhoanganh2002 closed 4 months ago
1
Added CI data and made changes to unllama_token_clf

#15 neeraja1504 closed 4 months ago
0
Padding Strategy

#14 upjabir opened 5 months ago
1
Assertion failed

#13 catalwaysright opened 5 months ago
2
downgraded to transformers 4.32.1 still got error

#12 qiuhaolu closed 5 months ago
4
TypeError: LlamaDecoderLayer.__init__() missing 1 required positional argument: 'layer_idx'

#11 frankdarkluo closed 5 months ago
4
Training on the custom dataset?

#10 25icecreamflavors opened 6 months ago
0
the inference function

#9 1259927114 opened 6 months ago
0
Not LlamaForSequenceClassification in modeling_llama.py

#8 thanhsang298 opened 6 months ago
1
Error while inferencing

#7 drmayu7 opened 7 months ago
1
Update README.md

#6 csroyli closed 7 months ago
0
Update modeling_llama.py

#5 csroyli closed 7 months ago
0
Cannot reproduce the results of this paper...

#4 coder4nlp closed 7 months ago
16
LoRA seems not training the linear head for classification

#3 mutetea closed 7 months ago
1
How to train with multiple GPUs

#2 xiaohei1001 closed 7 months ago
1
I'm stuck in a place, but I'm a beginner and I don't understand why, can you help me

#1 ckw-6 closed 9 months ago
4