Building on HF

Melvin Vivas PRO

melvindave

https://www.donvitocodes.com

AI & ML interests

Small Language Models, Vision, TTS, STT, Image Gen

Recent Activity

posted an update about 3 hours ago

Currently having a blast learning the transformers library. I noticed that model cards usually have Transformers code as usage examples. So I tried to figure out how to load a model just using the transformers library without using ollama, lmstudio, or llamacpp. Learned how to install dependencies required to make it work like pytorch and CUDA. I also used Conda for python environment dependencies. Once I got the model loaded and sample inference working, I made an API to serve it. I know it's very basic stuff for machine learning experts here in HF but I'm completely new to this so I'm happy to get it working! Model used: https://huggingface.co/Qwen/Qwen3-VL-8B-Instruct GPU: NVIDIA GeForce RTX 3090 Here's the result of my experimentation

replied to their post about 19 hours ago

Looking for receipts and documents datasets such as this for OCR purposes https://huggingface.co/datasets/naver-clova-ix/cord-v1 Has anyone seen similar ones? TIA

upvoted an article 1 day ago

🛡️ Nemotron PII: Synthesized Data for Privacy-Preserving AI

View all activity

Organizations

Posts 3

Post

Currently having a blast learning the transformers library.

I noticed that model cards usually have Transformers code as usage examples.

So I tried to figure out how to load a model just using the transformers library without using ollama, lmstudio, or llamacpp.

Learned how to install dependencies required to make it work like pytorch and CUDA. I also used Conda for python environment dependencies.

Once I got the model loaded and sample inference working, I made an API to serve it.

I know it's very basic stuff for machine learning experts here in HF but I'm completely new to this so I'm happy to get it working!

Model used: Qwen/Qwen3-VL-8B-Instruct
GPU: NVIDIA GeForce RTX 3090

Here's the result of my experimentation

Post

278