🤝 Open to Collab

Syed Mohaiminul Hoque

syedmohaiminulhoque

3 7

·

https://syedt1-github-io.vercel.app/

AI & ML interests

Natural Language Processing, LLMs, quantization, model unlearning, diffusion models

Recent Activity

reacted to davidjbrewer's post with 🔥 17 days ago

We use North Mini Code 1.0 locally (Ollama, q4_K_M) with OpenCode as our primary coding model. It's been the strongest small agentic coder we've tested. The one gap in daily work is that we can't paste screenshots of errors, terminal output or UI bugs into a session, since the model is text-only. Switching to a separate vision model mid-task breaks the workflow. Is native image input planned for a future North Mini Code release, for example by building in North Micro Vision's encoder? We'd test an early build.

updated a Space 18 days ago

syedmohaiminulhoque/agentic-doc-sim-streamlit

liked a Space 18 days ago

kulkas2pintu/wan777

View all activity

Organizations

syedmohaiminulhoque 's models 6

syedmohaiminulhoque/dkm-compression

syedmohaiminulhoque/constrained-discrete-diffusion

syedmohaiminulhoque/spotlight-attention-steering

Updated Apr 25 • 1

syedmohaiminulhoque/extending-activation-steering

Updated Apr 24 • 1

syedmohaiminulhoque/bipo-steering-vectors

syedmohaiminulhoque/transformer-from-scratch