fred blnch retweeted
You can now fine-tune Qwen3.8-27B for free with our notebook! 🔥
Local training works on 24GB VRAM.
Unsloth trains Qwen3.8-27B 1.5x faster with 50% less VRAM.
GitHub: github.com/unslothai/unsloth
Qwen3.8-27B Notebooks + Guide: unsloth.ai/docs/models/qwen3…
fred blnch retweeted
🔥Our paper PhyloLM got accepted at ICLR 2025 !🔥
In this work we show how easy it can be to infer relationship between LLMs by constructing trees and to predict their performances and behavior at a very low cost with @StePalminteri and @pyoudeyer ! Here is a brief recap ⬇️
fred blnch retweeted
Yasmine Belkaid : "Il y a 0,3 % d’investissement en France pour la recherche fondamentale, contre 1 % en Allemagne : couper encore plus, c'est irresponsable. On va atteindre un point de non-retour." #le710Inter
Post de circonstance. Le meilleur de 2024. Merci @FR_Conversation .
💦🏃♀️🚶♂️ Courir ou marcher sous la pluie ? Que vaut-il mieux faire ? Faites le bon choix avec nos conseils !
🔗 Basé sur l’article : urlr.me/m7zfq
#pluiesport #courseoumarche #santénaturelle #pluieconseils
fred blnch retweeted
ollama run llama3.1:405b
Tested in @tensorwave with @AMD MI300X
🤯
fred blnch retweeted
Artificial lifeforms are super fascinating to watch.
These self-organizing, self-replicating, “lifeforms” emerged from a continuous time cellular automata system called Flow-Lenia.
Lenia is a family of CAs generalizing Conway’s Game of Life to continuous space, time and states.
fred blnch retweeted
It's fast!!
Ollama now supports AMD graphics cards!
All the features of Ollama can now be accelerated by AMD graphics cards in preview on Ollama for Linux and Windows.
Try it 👇👇
ollama.com/download/windows
*video is not edited.
fred blnch retweeted
It’s inspiring to see co-founders & team leads at OpenAI (Greg being a prime example) writing code. The feeling invoked in me is almost like Medieval soldiers being inspired by the King fighting alongside them in battle (e.g., Richard the Lionheart, King Henry V, Charlemagne).
fred blnch retweeted
Can we align LLMs to honesty via instruction finetuning?
Can we instruct LLMs to say I Don't Know?
Can uncertainty learning improve prediction ability?
Excited to share R-Tuning, Refusal-Aware Instruction Tuning to tackle hallucination in LLMs.
Paper: arxiv.org/abs/2311.09677
fred blnch retweeted
Ollama works well with @llama_index and friends!
Run open-source models (ex. Mixtral 8x7b) with ollama + @llama_index + @qdrant_engine to create an all local retrieval augmented generation application.
Tutorial here
blog.llamaindex.ai/running-m…
Thank you @llama_index & @seldo!
fred blnch retweeted
RAG example w/ @streamlit, @llama_index, and Ollama.
Thank you @sroecker for your workshop at Red Hat developer's hands-on day in Germany!
github.com/sroecker/LLM_AppD…
Let's go open-source!