Get the latest tech news
AMD Releases AMD-135M: An Open-Source Small Language Model
AMD today announced 'AMD-135M' as their first small language model they are publicly releasing
AMD today announced "AMD-135M" as their first small language model they are publicly releasing. AMD-135M features speculative decoding and was trained from scratch using AMD Instinct MI250 accelerators with 670 billion tokens. There is also an AMD-Llama-135M-code variant that has an additional 20 billion tokens of code data.
Or read this on Phoronix
