Alexandros Liapatis

alexliap

·

AI & ML interests

Generative AI + Traditional ML

Recent Activity

reacted to FredyRivera-dev's post with 🚀 about 8 hours ago

We wrote a full technical guide on how to train a bilingual (ES/EN) LLM from scratch: TinyQwen. Covers: - Hybrid architecture based on Qwen3.5 - Pre-training with 15B tokens - Cost benchmark between H200 and B200 - Post-training with SFT + LoRA - Full code and data, open source With ~$11 of compute on an H200 we ran an initial training run, enough to validate the full architecture and pipeline. Blog post: https://aquiles-ai.vercel.app/blog/tinyqwen-from-scratch Technical feedback welcome, especially from anyone looking to replicate the pipeline with more compute.

reacted to Nymbo's post with 🔥 1 day ago

Introducing Inflect-v2, two exceptionally small, open-weight English TTS models at just 3.9M and 9.3M parameters. Both generate speech multiple times faster than real-time on CPU. Despite their size, Inflect-v2 delivers quality that is competitive with much larger lightweight TTS systems, including KittenTTS, Piper, and Supertonic-3. CPU, CUDA, PyTorch, and ONNX are supported. Apache 2.0. See it for yourselves: https://huggingface.co/owensong/Inflect-Micro-v2 https://huggingface.co/owensong/Inflect-Nano-v2 Try the Demos: https://huggingface.co/spaces/Nymbo/Inflect-TTS (unlimited CPU usage) https://huggingface.co/spaces/owensong/Inflect-v2 (ultra-fast ZeroGPU usage)

liked a dataset 1 day ago

HuggingFaceCode/stack-v3-train

View all activity

Organizations

alexliap 's Spaces 1

Deep Research Agent Demo

Intruct the agent to research a topic of your interest.