News AMD unveils AMD OLMo, its first 1B-parameter LLM with strong reasoning

[Admin]

AMD develops its own 1B-parameters OLMo large language model for a wide variety of applications that was trained on Instinct MI250 GPUs.

AMD unveils AMD OLMo, its first 1B-parameter LLM with strong reasoning : Read more

 

[subspruce]

nobody said anything about running it on Radeon.
oof

 

[usertests]

Additionally, AMD tested responsible AI benchmarks, such as ToxiGen (which measures toxic language, where a lower score is better)

Boooob

 

[Makaveli]

nobody said anything about running it on Radeon.
oof

I run Meta-Llama 3.1-8B on my 7900 XTX and that is a bigger model than the 1B mentioned above. These small models run well on NPU's so that is what I think the focus is here.