LLM360 (@llm360) / X

LLM360

137 posts

LLM360

@llm360

LLM360 is an open research lab enabling community-owned AGI through open-source large model research and development.

Joined November 2023

Pinned
LLM360
@llm360
Dec 5, 2025
To mark the 2nd anniversary of LLM360, we are proud to release K2-V2: a 70B reasoning-centric foundation model that delivers frontier capabilities. As a push for "360-open" transparency, we are releasing not only weights, but the full recipe: data composition, training code,
22K
LLM360
@llm360
Dec 11, 2023
🚀 1/7 We are thrilled to launch LLM360 — pushing the frontier of open-source & transparent LLMs! Starting with Amber (7B) & CrystalCoder (7B), we are releasing brand new pre-trained LLMs with all training code, data, and up to 360 model checkpoints. 🔗 llm360.ai
00:00
329K
LLM360
@llm360
May 29, 2024
Please welcome K2-65B🏔️, the most performant fully-open LLM released to date. As a blueprint for open-source AGI, we release all model checkpoints, code, logs, and data. About K2: 🧠65 billion parameters 🪟Fully transparent & reproducible 🔓Apache 2.0 📈Outperforms Llama 2 70B
00:00
138K
LLM360
@llm360
Oct 7, 2024
📢📢 We are releasing TxT360: a globally deduplicated dataset for LLM pretraining 🌐 99 Common Crawls 📘 14 Curated Sources 👨‍🍳 recipe to easily adjust data weighting and train the most performant models Dataset: huggingface.co/datasets/LLM36… Blog: huggingface.co/spaces/LLM360/…
52K
LLM360
@llm360
Jan 11, 2024
1/3 We are releasing CrystalChat 🔮 — a top-scoring 7B chat model, fully open source! As always, CrystalChat is released under Apache 2.0, along with all training data, checkpoints, and implementation details. Grab the model here: huggingface.co/LLM360/Crystal…
32K
LLM360
@llm360
Dec 11, 2023
Replying to @llm360
🔍 2/7 By releasing all data, code, & checkpoints, LLM360 makes it easy to reproduce results and build off our models for research and industry purposes. All models are released under Apache 2.0 license. Learn more Blog: short.llm360.ai/blog Paper: short.llm360.ai/paper
45K
LLM360
@llm360
Dec 21, 2023
1/3 We’re adding two new models to LLM360! Presenting AmberChat 💬 & AmberSafe 🦺. AmberChat is instruction tuned on Amber (7B) using @WizardLM_AI & @ShareGPT data. AmberSafe is DPO FT’d AmberChat using PKU-SafeRLHF data. AC: huggingface.co/LLM360/AmberCh… AS: huggingface.co/LLM360/AmberSa…
10K
LLM360
@llm360
Dec 11, 2023
Replying to @llm360
🙏 6/7 Huge thank you to the OSS ecosystem used in LLM360! @huggingface for hosting the models and data @wandb terrific metrics dashboards @AiEleuther set the precedent for OS LLMs with Pythia (and more) @lmsysorg great finetuning tools @LightningAI lit-llama was lit
8.1K
LLM360
@llm360
Oct 23, 2024
📣Proud to share Web2Code: a Large-scale Webpage-to-Code Dataset and Evaluation Framework for Multimodal LLMs was accepted to @NeurIPSConf 2024! About Web2Code: 📸 novel image + html dataset 📈webpage code gen benchmark 🧠CrystalChat-7B-Web2Code Blog: mbzuai-llm.github.io/webpage2code/
4.3K
LLM360
@llm360
Dec 19, 2024
The LLM360 team is hiring! 🚀 We welcome researchers and ML engineers to join our team to push the frontier of AI research. You'll be deeply involved and gain firsthand experience in large model training. Join us in our mission of making AGI open to all. For more information,
docs.google.com
LLM360 Full-time/Intern Application
We are a team dedicated to training the best open language models and advancing AI through world models and real-world simulators. Our new lab will be located in Sunnyvale, CA, and we are excited to...
13K
LLM360
@llm360
Dec 11, 2023
Replying to @llm360
🌟 3/7 Amber, a 7B English LLM, is pre-trained on 1.2T tokens. See Amber’s emergent capabilities over 360 checkpoints & dive into 6.8TB of data. Model: short.llm360.ai/amber-model Metrics: short.llm360.ai/amber-metrics Data: short.llm360.ai/amber-data Code: short.llm360.ai/amber-code
7.1K
LLM360
@llm360
Dec 11, 2023
Replying to @llm360
🔮 4/7 CrystalCoder, a 7B code & text model, combines the best of StarCoder & Llama. Trained w/ 1.4T tokens on @cerebras Condor Galaxy 1. Model: short.llm360.ai/crystalcoder-m… Metrics: short.llm360.ai/crystalcoder-m… Data: short.llm360.ai/crystalcoder-d… Code: short.llm360.ai/crystalcoder-c…
4.3K
LLM360
@llm360
Oct 15, 2024
The LLM360 team had a great time @COLM_conf last week! It was a big week releasing TxT360, a revamped Analysis360 repo, and Decentralized Arena w/ @MaitrixOrg...along with poster sessions for two accepted papers! See you next year!
5.7K
LLM360
@llm360
Dec 4, 2024
Congrats to CMU’s new FLAME Center for LLMs and Foundation Models 🔥! cc @zicokolter, @gneubig, @AdtRaghunathan, @XiongChenyan cmu.edu/flame/ “Fundamental research into powerful, open, and responsible foundation models” — we resonate with this goal and think it’s vital
7.4K