Fabrice Harel-Canada

Custom torch.utils.data.DataLoader.collate_fn

1

I'm working on a series of data augmentations for text and have implemented their use via the `torch.utils.data.DataLoader.collate_fn` but `jiant` appears to be using this function already. Is there a...

**Describe the bug** When using `textattack.augmentation.recipes.CheckListAugmenter` on the `yahoo_answers_topics` dataset in Huggingface, I get an error: ``` ... File "~\textattack\transformations\word_swaps\word_swap_change_number.py", line 108, in _alter_number num_list = np.random.randint(max(num - change, 1),...

Hi there, I'm trying to use `apricot` to help find a diverse set of texts. When I use the `fit` method, everything works intuitively. However, when I start using the...

Llama-3 Inference and Uploading to Huggingface

7

I'm trying to fine-tune Llama-3-8B and 70B with LoRA on a custom drug detection dataset and upload it to Huggingface so that it fits nicely into an existing evaluation zero-shot...

### Motivation Right now it appears that InternVL only supports SFT, but it would be helpful to expand on this with preference datasets. This would allow for an even more...

Does xtuner support DPO for InternVL?

1

I am trying to do a custom DPO fine-tuning for `internvl_v2_internlm2_2b_lora_finetune`, but the default config is oriented towards vanilla supervised fine-tuning with images. I tried to compare / incorporate changes...