Deprecated: The each() function is deprecated. This message will be suppressed on further calls in /home/zhenxiangba/zhenxiangba.com/public_html/phproxy-improved-master/index.php on line 456
monsoon-nlp (Nick Doiron)
[go: Go Back, main page]
Hugging Face's logo
Nick Doiron's picture
51 69 213

Nick Doiron

monsoon-nlp
AfricaTC's profile picture mjsolidarios's profile picture xinfyxinfy's profile picture
Ā·
https://mapmeld.com/plant-based-llms/

AI & ML interests

biology and multilingual models

Recent Activity

liked a model 10 days ago
orgava/dna-bacteria-jepa
reacted to mmhamdy's post with šŸš€ 10 days ago
Human brains don't recreate every pixel to understand the world! Most current models in genomics, proteomics, and single-cell transcriptomics rely on generative objectives like masked language modeling or next token prediction. While effective, these architectures waste significant capacity reconstructing raw, noisy sequence details that may not carry functional biological meaning. But a promising, more efficient alternative is emerging: Joint-Embedding Predictive Architecture (JEPA) Originally introduced by Yann LeCun for computer vision, JEPA is a non-generative, self-supervised learning (SSL) framework. Instead of predicting raw inputs, it operates as a world model that predicts abstract semantic embeddings in latent space. Recently, the JEPA framework (and its more efficient LeJEPA variant) has been adapted into the biological sciences to develop performing foundation models and to improve on already existing ones. It's interesting how each adaptation modified and tailored JEPA to suit its specific biological domain, whether by experimenting with different backbones or complementing the objective with other loss terms. For example, JEPA-DNA and ProteinJEPA used JEPA as a continual pre-training framework to enhance existing foundation models without training from scratch, while Cell-JEPA and JEPA-DNA employed a hybrid objective that combines the JEPA loss with a traditional language modeling loss. The article below provides an overview of these implementations, along with others that came out this year. As always, your thoughts and feedback are welcome and highly appreciated! Link to the article is in the first comment šŸ‘‡
reacted to pankajpandey-dev's post with šŸ”„ 18 days ago
šŸ‡®šŸ‡³ Qwen3-4B Hindi Instruct v2 ā€” a Hindi LLM that runs on your own machine Most strong Hindi-capable models are either huge or cloud-only. I wanted one that's small enough to run locally but actually follows instructions in Hindi ā€” so I fine-tuned Qwen3-4B on 10K Hindi instruction pairs and shipped it with a full GGUF quant ladder. āœ… Fine-tune (16-bit): huggingface.co/pankajpandey-dev/Qwen3-4B-Hindi-Instruct-v2 āœ… GGUF (Q4/Q5/Q8): huggingface.co/pankajpandey-dev/Qwen3-4B-Hindi-Instruct-v2-GGUF Runs in Ollama, llama.cpp, and LM Studio. The Q4_K_M is just 2.5 GB ā€” fits comfortably on a laptop, CPU or GPU. Part of my Hindi LLM Series ā€” building openly-licensed Indic models for local and edge use. More coming (Gemma next). Feedback welcome šŸ™ #Hindi #IndicNLP #GGUF #LocalLLM #Qwen
View all activity

Organizations

BigScience Workshop's profile picture Spaces-explorers's profile picture BigCode's profile picture Blog-explorers's profile picture Scary Snake's profile picture Hugging Face Discord Community's profile picture Hugging Face Context Course's profile picture