s3nh's picture

s3nh

s3nh

·

AI & ML interests

Quantization, LLMs, Deep Learning for good. Follow me if you like my work. Patreon.com/s3nh

Recent Activity

Reacted to Xenova's post with 🔥 5 days ago

Have you tried out 🤗 Transformers.js v3? Here are the new features: ⚡ WebGPU support (up to 100x faster than WASM) 🔢 New quantization formats (dtypes) 🏛 120 supported architectures in total 📂 25 new example projects and templates 🤖 Over 1200 pre-converted models 🌐 Node.js (ESM + CJS), Deno, and Bun compatibility 🏡 A new home on GitHub and NPM Get started with `npm i @huggingface/transformers`. Learn more in our blog post: https://huggingface.co/blog/transformersjs-v3

Reacted to ArthurZ's post with 🔥 8 days ago

Native tensor parallel has landed in transformers!!! https://github.com/huggingface/transformers/pull/34184 thanks a lot to the torch team for their support! Contributions are welcome to support more models! 🔥

Reacted to reach-vb's post with 🔥 9 days ago

What a brilliant week for Open Source AI! Qwen 2.5 Coder by Alibaba - 0.5B / 1.5B / 3B / 7B / 14B/ 32B (Base + Instruct) Code generation LLMs, with 32B tackling giants like Gemnini 1.5 Pro, Claude Sonnet https://huggingface.co/collections/Qwen/qwen25-coder-66eaa22e6f99801bf65b0c2f LLM2CLIP from Microsoft - Leverage LLMs to train ultra-powerful CLIP models! Boosts performance over the previous SOTA by ~17% https://huggingface.co/collections/microsoft/llm2clip-672323a266173cfa40b32d4c Athene v2 Chat & Agent by NexusFlow - SoTA general LLM fine-tuned from Qwen 2.5 72B excels at Chat + Function Calling/ JSON/ Agents https://huggingface.co/collections/Nexusflow/athene-v2-6735b85e505981a794fb02cc Orca Agent Instruct by Microsoft - 1 million instruct pairs covering text editing, creative writing, coding, reading comprehension, etc - permissively licensed https://huggingface.co/datasets/microsoft/orca-agentinstruct-1M-v1 Ultravox by FixieAI - 70B/ 8B model approaching GPT4o level, pick any LLM, train an adapter with Whisper as Audio Encoder https://huggingface.co/collections/reach-vb/ultravox-audio-language-model-release-67373b602af0a52b2a88ae71 JanusFlow 1.3 by DeepSeek - Next iteration of their Unified MultiModal LLM Janus with RectifiedFlow https://huggingface.co/deepseek-ai/JanusFlow-1.3B Common Corpus by Pleais - 2,003,039,184,047 multilingual, commercially permissive and high quality tokens! https://huggingface.co/datasets/PleIAs/common_corpus I'm sure I missed a lot, can't wait for the next week! Put down in comments what I missed! 🤗

View all activity

Organizations

s3nh's activity

upvoted a collection 20 days ago

Flux LoRA Collections

Flux THE LoRA • 91 items • Updated about 13 hours ago • 29

upvoted 3 papers 5 months ago

PIA: Your Personalized Image Animator via Plug-and-Play Modules in Text-to-Image Models

Paper • 2312.13964 • Published Dec 21, 2023 • 18

MotionBooth: Motion-Aware Customized Text-to-Video Generation

Paper • 2406.17758 • Published Jun 25 • 18

FoleyCrafter: Bring Silent Videos to Life with Lifelike and Synchronized Sounds

Paper • 2407.01494 • Published Jul 1 • 13

upvoted an article 5 months ago

Article

Image-based search engine

By

•

Jul 4

• 23

upvoted a paper 6 months ago

LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning

Paper • 2401.01325 • Published Jan 2 • 26

upvoted 2 collections 11 months ago

Merged models

Mering experiments. • 2 items • Updated Jan 5 • 1

S3nh GGUFs collection

GGUF converted models, sorted by creation date. • 5 items • Updated Jan 2 • 1

upvoted a paper over 1 year ago

To Adapt or Not to Adapt? Real-Time Adaptation for Semantic Segmentation

Paper • 2307.15063 • Published Jul 27, 2023 • 17