pyreft
pyreft copied to clipboard
stanfordnlp
ReFT: Representation Finetuning for Language Models
I have an error on trainer.trian(). Plese help me! ## Error ``` TypeError: LlamaForCausalLM.forward() got an unexpected keyword argument 'unit_locations' ``` ## code ```python import pyreft import torch import transformers...
I was training and saving REFT modules for the RoBERTa model. But loading them seems to be not possible with the current implementation. I get the following Error: ``` Traceback...
Hey team, I am having issues with large datasets (~10k samples or more). Calling the `make_last_position_supervised_data_module` function is slower than the training itself. The root cause is that the function...
I want to use some code data sets to fine-tune the basic model in the code task field. However, when I am evaluating, I hope to convert the generated reft...
**Descriptions:** By taking a quick look at the PEFT library, it wraps nn.module as a PEFT nn.module which accepts gradient, is trainable, and just like another nn.module. This is highly...
**Descriptions:** For customizable interventions, people might want to save the interventions with their customized arguments. For instance, the dropout ratio, the activation function type or whether to add a special...
1. Are there plans for inference support. This is needed if it's to be used by devs in production. 2. Is fine tuning much faster than LoRA? - Optimization and...
The ReadMe mentions the ability to serve at scale with continuous batching. Even if not vLLM or TGI, is there some work that someone could point me to on this?...
As shown by issue #69, Pyreft did not work well with tensorboard callbacks. We may need to modify Pyvene to remove the serialization of "types" in configs.
Metadata
Owner
Metadata
ReFT: Representation Finetuning for Language Models