All Questions
6 questions
0
votes
0
answers
42
views
LoRA Adapter Loading Issue with Llama 3.1 8B - Missing Keys Warning
I'm having trouble loading my LoRA adapters for inference after fine-tuning Llama 3.1 8B. When I try to load the adapter files in a new session, I get a warning about missing adapter keys:
/usr/local/...
0
votes
1
answer
1k
views
Can I dynamically add or remove LoRA weights in the transformer library like diffusers
I see that in the diffuser library, there is this feature to dynamically add and remove LoRA weights based on this article https://github.com/huggingface/blog/blob/main/lora-adapters-dynamic-loading....
2
votes
5
answers
4k
views
PyTorch: AttributeError: 'torch.dtype' object has no attribute 'itemsize'
I am trying to follow this article on medium Article.
I had a few problems with it so the remain chang eI did was to the TrainingArguments object I added gradient_checkpointing_kwargs={'use_reentrant':...
- 1,342
2
votes
1
answer
651
views
Why no log for training model, and key_error for 'eval_loss'?
I am trying to build a LORA model for sentiment analysis as part of an academic project. However, when training the model, I keep getting an error when computing the loss. I have tried a bunch of ...
- 59
0
votes
1
answer
1k
views
Huggingface peft error message AttributeError: 'Linear8bitLt' object has no attribute 'state'
I'm loading a huggingface dataset and Mistral-7B-Instruct-v0.1 to finetune for detection of sentiment. I'm running the following notebook, but updated it to use the above model and dataset instead. I ...
0
votes
1
answer
421
views
perform peft with lora on flan-t5 model causing no executable batch size error
I'm trying to perform PEFT with LoRA. I'm using the Google flan-T5 base model. I'm using the Python code below. I'm running the code with an nvidia GPU with 8 GB of ram on Ubuntu server 18.04 LTS. In ...
- 4,605