Nguyen Khanh Linh

Finetuned model doesn't load in eval/inference

1

After I finetuned a pretrained model on my custom data, I tried to eval it. My code is as below ``` from neuspell.seq_modeling.helpers import load_data, train_validation_split from neuspell.seq_modeling.helpers import get_tokens...

IndexError: index out of range in self

1

Hi @neuspell team. I really appreciated the efforts that you guys put into this research project. I would like to try on some Vietnamese model, for example "vinai/phobert-base". But I...

CUDA out of memory

3

Hi, I tried to train my own custom data using some large pretrained model (multilingual) such as multilingual BERT or XML roBERTa, and even if I tried reducing my batch...

Cannot do inference on any trained models

1

As title, whenever I tried to do interactive.py, for student model or teach model, it will be like this ``` File "/ldap_home/khanhlinh.nguyen/notebooks/MNMT/multilingual-kd-pytorch/fairseq/tasks/fairseq_task.py", line 56, in dataset raise KeyError('Dataset not loaded:...

Connection error when running fastrag.rest_api_application

4

I ran this separately just to test the fastRAG pipeline `python -m fastrag.rest_api.application --config=config/my_config.yaml --app_type qa` The output looks like this `e torch.utils._pytree.register_pytree_node instead. _torch_pytree._register_pytree_node( config.json: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 794/794 [00:00

- Fix JSON error when there is incomplete prompt leading to failed json generation - Add more fields in the summariaztion such as methodology, discussion, data used etc - Add...

Linh commit notebook for Building Secure Agentic AI Systems with Safe…

4

…ty Guardrails (correct CLA) Defending Against Jailbreaks using Google ADK with LLM-as-a-Judge and Model Armor In this notebook, you'll learn how to build production-ready Agentic AI systems with comprehensive safety...