Vitor Alcantara Batista
Vitor Alcantara Batista
How can I set the current page of a PDF after it loads?
## The problem I'd like to have autocomplete in searchbox using SearchKit 2.4 even if I have to do some custom code, but couldn't find a guide or orientation on...
Hi, I have a QA dataset in SQuAD format: (context, question, answer) triples. How to finetune Qwen with this dataset using HuggingFace PEFT (https://huggingface.co/docs/peft/main/en/index) library? When I use Bitsandbytes to...
Hi, I'm trying to figure out how to prepare data and fine tuning this T5 base model (https://huggingface.co/unicamp-dl/ptt5-base-t5-vocab) with this squad dataset (https://huggingface.co/datasets/squad_v1_pt) I downloaded data from hugging face to...
## CKAN version 2.10 ## Describe the bug I deployed CKAN using docker into a container with 4Gb RAM and 2 vCPUs. We are using s3filestore plugin (https://github.com/keitaroinc/ckanext-s3filestore/). When uploading...
HI, I'm trying to create a dense representations from my corpus and search paragraphs/phrases by keywords or a question. I don't have labeled Questions and Answers and I don't need...
I'm trying to persist logged user between refreshes with code below in React app ``` const gtoken = localStorage.getItem('g-token'); if (gtoken !== undefined) { const decoded: { email: string }...
I'm trying to finetune Llama2 70B using a NVIDIA A100 with 80Gb, but even with batch-size = 1 I'm getting OOM error. I'm using LoRA with quantization this way: `plugins...
It would be very helpful if lit-gpt provides support for the new models Qwen (https://huggingface.co/Qwen). They have strong performance compared to other open source models.
I am relatively new to sglang. I managed to deploy 70B parameter models using 2 nodes. I noticed that each node has its own endpoint. I would like to understand...