Victor Mustar's picture

Building on HF

Victor Mustar PRO

victor

huggingface

·

victormustar

AI & ML interests

Building the UX of this website

Recent Activity

liked a model about 8 hours ago

Mazino0/fire-red-streaming-vad-onnx

liked a model 1 day ago

microsoft/Phi-4-reasoning-vision-15B

reacted to mayafree's post with 🚀 1 day ago

I built a Space that lets you switch between all three Qwen3.5 official collection models in a single interface. https://huggingface.co/spaces/MAYA-AI/QWEN-3_5-CHAT The architecture is the key part. Instead of using Gradio as the UI, I use it purely as an API engine. FastAPI serves a fully custom HTML/JS frontend that calls /gradio_api/call/chat via SSE streaming. No DOM conflicts, no layout constraints. Four main features: instant model switching with automatic spec adjustment (max tokens, temperature ceiling, Vision availability all update per model), Thinking Mode via /think prefix with collapsible reasoning chain, Vision image upload via base64 conversion, and HF OAuth implemented directly at the FastAPI level. For model selection: 122B-A10B with Thinking Mode for math, logic, and agents. 27B for writing, translation, and instruction following. 35B-A3B for fast everyday questions. A few surprises during development — Gradio 6.x removed several parameters quietly, base64 image strings broke gr.Image(type="pil") so I switched to gr.Textbox with backend PIL conversion, and Thinking Mode parsing needed a full rewrite with indexOf instead of regex. Thanks to the Qwen team for making this possible. Try it out and let me know what you think. #Qwen3 #Qwen35 #OpenSourceAI #HuggingFace #LLM #ThinkingAI #vidraft #MultimodalAI

View all activity

Organizations

submitted a paper to Daily Papers 8 days ago

DualPath: Breaking the Storage Bandwidth Bottleneck in Agentic LLM Inference

Paper • 2602.21548 • Published 9 days ago • 37