Hafedh Hichri's picture

Hafedh Hichri

not-lain

·

https://not-lain.github.io

AI & ML interests

custom AI models with HF integration, multimodal rag and open-source contributions && may or may not be a huggingface fellow

Recent Activity

liked a model about 6 hours ago

mlx-community/INTELLECT-1-Instruct-6bit

Reacted to hexgrad's post with 🔥 about 6 hours ago

`self.brag():` Kokoro finally got 300 votes in https://huggingface.co/spaces/Pendrokar/TTS-Spaces-Arena after @Pendrokar was kind enough to add it 3 weeks ago. Discounting the small sample size of votes, I think it is safe to say that https://huggingface.co/spaces/hexgrad/Kokoro-TTS is currently a top 3 model among the contenders in that Arena. This is notable because: - At 82M params, Kokoro is one of the smaller models in the Arena - MeloTTS has 52M params - F5 TTS has 330M params - XTTSv2 has 467M params

upvoted an article 1 day ago

Towards a Fully Arabic Retrieval-Augmented Generation (RAG) Pipeline:

View all activity

Articles

PyTorchModelHubMixin: Bridging the Gap for Custom AI Models on Hugging Face

RAG chatbot using llama3

Image-based search engine

Train custom AI models with the trainer API and adapt them to 🤗

Custom architectures with HuggingFace 🤗

Organizations

not-lain's activity

upvoted an article 1 day ago

Article

Towards a Fully Arabic Retrieval-Augmented Generation (RAG) Pipeline:

By

•

2 days ago

• 5

upvoted 2 articles 4 days ago

Article

To what extent are we responsible for our content and how to create safer Spaces?

By

•

Aug 30

• 3

Article

Use Models from the Hugging Face Hub in LM Studio

By

•

4 days ago

• 73

upvoted an article 6 days ago

Article

Let’s make a generation of amazing image generation models

By

•

6 days ago

• 33

upvoted 2 articles 11 days ago

Article

Procedural Knowledge in Pretraining Drives Reasoning in Large Language Models

By

•

11 days ago

• 2

Article

Introducing Observers: AI Observability with Hugging Face datasets through a lightweight SDK

By

•

12 days ago

• 34

upvoted an article 13 days ago

Article

Low Code Large Language Model Alignment

By

•

14 days ago

• 13

upvoted an article 19 days ago

Article

Releasing the largest multilingual open pretraining dataset

By

•

19 days ago

• 97

upvoted a collection 20 days ago

Marqo-Ecommerce-Embeddings

State-of-the-art embedding models fine-tuned for the ecommerce domain. +67% increase in evaluation metrics vs ViT-B-16-SigLIP. • 10 items • Updated 18 days ago • 17

upvoted an article 20 days ago

Article

Hugging Face Welcomes the Qwen2.5-Coder Series

By

•

21 days ago

• 7

upvoted an article 21 days ago

Article

PyTorchModelHubMixin: Bridging the Gap for Custom AI Models on Hugging Face

By

•

21 days ago

• 12

upvoted an article 23 days ago

Article

Inference Endpoints Changelog 🚀

By

•

Oct 11

• 18

upvoted a paper 23 days ago

Mixture-of-Transformers: A Sparse and Scalable Architecture for Multi-Modal Foundation Models

Paper • 2411.04996 • Published 25 days ago • 49

upvoted 3 articles 27 days ago

Article

ColPali: Efficient Document Retrieval with Vision Language Models 👀

By

•

Jul 5

• 169

Article

Introducing GGUF-my-LoRA

By

•

Nov 1

• 11

Article

Recipe: Preparing Multilingual Speech Datasets for TTS Training

By

•

28 days ago

• 14

upvoted a collection 28 days ago

AMD-OLMo

AMD-OLMo are a series of 1 billion parameter language models trained by AMD on AMD Instinct™ MI250 GPUs based on OLMo. • 4 items • Updated Oct 31 • 17

upvoted an article about 1 month ago

Article

Visually Multilingual: Introducing mcdse-2b

By

•

Oct 27

• 37

upvoted a paper about 1 month ago

VidToMe: Video Token Merging for Zero-Shot Video Editing

Paper • 2312.10656 • Published Dec 17, 2023 • 10

upvoted an article about 1 month ago

Article

Hugging Face welcomes the Aya Expanse family of multilingual models

By

•

Oct 24

• 10