17 7 34

Paul Lemaistre PRO

paulml

AI & ML interests

TTS - LLM - Agents | Lead Dev @ TW3 Partners

Recent Activity

upvoted an article about 18 hours ago

How I Built Lightning-Fast Vector Search for Legal Documents

reacted to ronantakizawa's post with 👍 about 18 hours ago

Introducing AWQ and GPTQ quantized versions of SmolVLM from Hugging Face! These models only had their text models quantized, and had a 50% model size reduction (4GB~2GB) while keeping model degradation under 1% on the DocVQA benchmark. #huggingface #smolvlm #smollm https://huggingface.co/ronantakizawa/SmolVLM-Instruct-awq https://huggingface.co/ronantakizawa/SmolVLM-Instruct-gptq

posted an update about 18 hours ago

Qwen3-VL-4B is incredibly easy to fine-tune! We've trained the first DSE model based on this model, and it's already performing at the same level as Jina v4! While Jina Embeddings v4 is built on Qwen2.5-VL-3B (which has a non-commercial license), our model is based on Qwen3-VL-4B and released under Apache 2.0—making it fully commercially permissive. Check out our DSE model here: https://huggingface.co/racineai/QwenAmann-4B-dse

View all activity

Organizations

Posts 1

Post

535

Qwen3-VL-4B is incredibly easy to fine-tune!
We've trained the first DSE model based on this model, and it's already performing at the same level as Jina v4!

While Jina Embeddings v4 is built on Qwen2.5-VL-3B (which has a non-commercial license), our model is based on Qwen3-VL-4B and released under Apache 2.0—making it fully commercially permissive.

Check out our DSE model here:
racineai/QwenAmann-4B-dse

View all Posts