🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Start fine-tuning Qwen3-14B for free on Google Colab: colab.research.google.com/drive/1EscYgLM…

My first Axolotl on a SLURM multi-node cluster! I'm unsure what to expect! But it's fun! 😎

🚀 Async-RL is now available with Nous Research Atropos and Axolotl! We've created a plugin for tighter RL iterations that leverages Atropos' optimized asynchronous rollouts. Check out the plugin and get started: github.com/axolotl-ai-clo…

Never got so much good swag 😭 now looking for some good API credits 😇 Nous Research Axolotl

Verdict at Nous Research RL hackathon! Your calibrated and low-variance LLM-as-a-judge is a reward model 🙈

Model Merging in Pre-training of Large Language Models "We present the Pre-trained Model Averaging (PMA) strategy, a novel framework for model merging during LLM pre-training. Through extensive experiments across model scales (from millions to over 100B parameters), we

Come hack with us in SF June 8th

Come join us on June 8th at Shack15 to accelerate AI on AMD, ARM, and other accelerators!

Current status: v0.9.2 github.com/axolotl-ai-clo…

Spot the runpod truck in sf and get $250 in gpu credits Snap a pic + tag Runpod and we'll send you a credit code 🤝 Hint: it's right by AI Engineer

Using Google Cloud 🤝 Axolotl can help you streamline your large Multimodal finetuning workflows.

Deploy Axolotl with Google Cloud for your production workloads with simple configuration based orchestration.

Mistral AI 64 comrades airship cooperative Magistral Small is an open-weight model, and is available for self-deployment under the Apache 2.0 license. You can use it with the following frameworks: - vllm (recommended): huggingface.co/mistralai/Magi… The community has prepared quantized versions of the model that can be used

Hacker house was in full force last week for AI Engineer with events with Runpod plus collab with Google Cloud... sailing with team + Thomas Capelle visits SHACK15 ... ⛵️🔥 😊

Looking to fine-tune models? Meet Axolotl 💚 an open-source tool that simplifies the entire fine-tuning pipeline. Learn how to get started with our tutorial covering how to fine-tune Llama 3 🦙 koyeb.com/tutorials/usin…

Training qwe3 with qwen2.5 template works just fine. Way easier to make everything work, and just one line change in Axolotl