The claim that it is better than GPT3.5, in practice, should be taken with a grain of salt, since the benchmarks themselves aren't... ideal.
Despite the questionable marketing claim, it is a great LLM for other reasons.
Despite the questionable marketing claim, it is a great LLM for other reasons.
On the other hand, if the base instruct model is good enough to roughly match it then the fine tunes will be interesting for sure.