-
I was trying to use xlora for combining Flan-T5 LoRAs and ran into error within apply_scalings_to_x, does xLoRA support seq2seq models such as Flan-T5 and BART ?
-
### System Info
- `transformers` version: 4.40.0
- Platform: Linux-6.1.58+-x86_64-with-glibc2.35
- Python version: 3.10.12
- Huggingface_hub version: 0.22.2
- Safetensors version: 0.4.3
- Accele…
-
-
### Prerequisites
- [X] I have read the [documentation](https://hf.co/docs/autotrain).
- [X] I have checked other issues for similar problems.
### Backend
Local
### Interface Used
UI
…
-
**Sequence-to-sequence** (seq2seq) models ([Sutskever et al., 2014](https://papers.nips.cc/paper/5346-sequence-to-sequence-learning-with-neural-networks.pdf), [Cho et al., 2014](http://emnlp2014.org/p…
-
Hello @EricLBuehler, opening this issue as part of T5 Seq2Seq model architecture support in mistral.rs. (As discussed)
Relates to: #156
-
Hello, I want to replicate the results of Table 2 on your paper - in particular the performances of the Seq2Seq and BUTLER agents. After I have trained the two agents, what scripts should I run to rep…
-
https://github.com/bentrevett/pytorch-seq2seq
-
请问这两个版本有什么区别?
-
Hi!
Is it trivial to adapt the AST architecture to do sequence to sequence classification? My input data has a label for each audio sample and my goal is to classify each sample in the data.