Olmo by Ai2

“Ai2 (Ollmo, Tulu, ...) and the recent model from Aleph Alpha if you want to learn more.”

“Not Open, just willing to state what they fed into the training.”

“There are models that do that, for example the Olmo family of models”

“That 7B model also worked well in my experiments on a laptop.”

“no one is using Olmo for "serious" work”

“It's not super helpful, especially as a sovereign government initiative to build an also-ran”

“AI2 complete transparency including training data, code, intermediate checkpoints, and detailed logs for reproducibility and scientific rigor”

“We have models here in the states like OLMo that could receive more investing”

“Allen AI is fighting the good fight with their Olmo models”

“very compelling capabilities where the dataset, training process, and final weights are all open”

“This olmo uses random data of totally infringing license database such a StackEdu”

“Check out the OLMo family from the Allen Institute for AI”

“Ai2's OLMo, EleutherAI's Pythia, and LLM360's Amber are actually open source, top to bottom”

“ethically sourced, open source LLMs exist! Check out eg Olmo by Allen AI”

“fully open source models that are comparable to o1-mini (OLMo)”

“Allen AI do not get enough love. They are doing GenAI how it should have always been done.”

“Olmo 3 from AllenAI, and K2 Think V2 from Mohamed bin Zayed University of Artificial Intelligence are both fully open, but not as capable as the Nemotron family.”

“If you really want to see fully open training pipelines for modern LLMs, Olmo”

“It is not on the “frontier” in any meaningful way.”

“sharing not just models and even training data, but also the training code and methodologies”

“where the have open weights, checkpoints, training data, and training process”

“Weights, datasets, code, multiple checkpoints...”

“one of the only really good models with open training data”

“performance-competitive with Gemini in several benchmarks”

“the only SOTA-ish model that has fully open source code and data”

“Worked for the first message but got progressively more unstable.”

“mine would perform very poorly when the conversation got past 1 turn”

“This type of model is as open as is physically possible, and represents a real improvement in user agency”

“if they're really being open about the whole pipeline, they have to include everything”

“I really appreciate that you all are releasing true open source models complete with data, training code and weights.”

“there is a broad practical application served here for developers who need to figure out a project on their own hardware”

“We are competitive with open weights models in general, just a couple points behind best Qwen.”

“it admitted that it left out the fourth stomach because it was small, and claimed that the rumination wasn't "true" in some sense”

“There's a lot of companies using fine tuned Qwen 3 models that might want to switch to Olmo now that we have released a 32B base model.”

“I'm wondering why it thinks that it was developed by OpenAI.”

“this one is the closest to being competitive with closed models”

“Giraffes are not kosher because they do not chew their cud, even though they have split hooves.”

“they also publish lot of data augmentation results including European language performance”

“It might be an OpenWebUI bug but not so promising”

“a huge achievement for a truly open source model, and a necessary check and balance on corporate control of AI”