I remember a full dozen years ago the feeling of independence, tinged with some slight digital survivalism, of running a local version of Wikipedia from my Nexus One smartphone. It was cool, but I used that feature on maybe a couple of flights. I know better now that I feel a similar impulse about running powerful LLMs from my smartphone.
Tag: LLMs
Replace a fine-tuned text-davinci-003 with Mixtral 8x7B
In a few short hours, OpenAI will shut down access to a few old large language models, the text-davinci series. Everyone who depended for some project on a fine-tuned version of these models and who hasn’t found a replacement yet might soon feel some pain. I was in that cohort until I found out how …