The post gives concrete LoRA SFT figures and a linked recipe for post-training a 1T-parameter model on one node, useful for engineers planning similar fine-tuning.
TRL has day-0 support to post-train Le Chonk on a single node 🤯
LoRA SFT on a 1T-parameter model, training adapters on top of FP8 weights:
⚡ 32.7k tokens per step in ~8 seconds
💾 142 GiB per GPU on 8× B300
🔀 Expert parallelism + FSDP
Open weights = open training after all ;)
Today, we release the weights of a new and improved Le Chonk, advancing the open frontier for agentic coding and cybersecurity. 💻 Built to build: Le Chonk ranks #1 on @cognition’s FrontierCode among open models, and sets a new benchmark for Pareto efficiency on @artificialanalysis. 🛡 Built to defend: State-of-the-art in cyberdefense, put through the paces by the world's leading cyber vendors, including @CrowdStrike, @cloudflare, @rubrik, @zscaler, and others. Built for sovereignty: Make it yours. Download the weights on @huggingface , customize it with Mistral Forge, and deploy it wherever you need it. Read more from our team and customers 👇:
Lewis Tunstall · x.comPublished · added here
Original title: TRL has day-0 support to post-train Le Chonk on a single node 🤯
