Yet Another Bookmarks Service



[https://medium.com/@andreasmuelder/large-language-models-for-domain-specific-language-generation-how-to-train-your-dragon-0b5360e8ed76] - - public:mzimmerm
ai, article, code, doc, generate, llm, train - 7 | id:1489780 -

training a model like Llama with 2.7 billion parameters outperformed a larger model like Vicuna with 13 billion parameters. Especially when considering resource consumption, this might be a good alternative to using a 7B Foundation model instead of a full-blown ChatGPT. The best price-to-performance base model for our use case turned out to be Mistral 7b. The model is compact enough to fit into an affordable GPU with 24GB VRAM and outperforms the other models with 7B parameters.

[https://en.wikipedia.org/wiki/Coroutine] - - public:mzimmerm
computer, coroutine, generate, good, multi, program, science, software, thread, yield - 10 | id:1485369 -

Coroutine is a routine which can yield. Coroutines are typically scheduled cooperatively (=non-preemptively). Coroutines are similar to threads, although threads are typically scheduled preemptively (scheduler pre-empts=forces execution to pause and yield, even without yield in the language)

Follow Tags