Code Llama, a state-of-the-art large language model for coding

Re:Code Llama, a state-of-the-art large language model for c... by julianeon on Thursday August 24, 2023 @04:08PM (#37253898)

What I want is even simpler: just an API that you make requests to and receive answers back. Surprisingly hard to find, outside OpenAI that is.

[ Parent | on HN ]

Re:Code Llama, a state-of-the-art large language model for c... by ingridpan on Thursday August 24, 2023 @04:15PM (#37253978)

https://gradient.ai/ is doing that with llama2

[ Parent | on HN ]

Re:Code Llama, a state-of-the-art large language model for c... by worldsayshi on Thursday August 24, 2023 @05:00PM (#37254482)

Looks really promising. I wonder if the similar pricing to OpenAI means that Gradient is also(?) bleeding money even if they get a good customer base. Or are these prices sustainable over time?

[ Parent | on HN ]

Re:Code Llama, a state-of-the-art large language model for c... by ingridpan on Thursday August 24, 2023 @05:19PM (#37254681)

I think OpenAI is overcharging... because they can

[ Parent | on HN ]

Re:Code Llama, a state-of-the-art large language model for c... by worldsayshi on Friday August 25, 2023 @12:06PM (#37263293)

Yeah it's even cheaper. Although it looks like it's about the same in proportion to approx model size/expected quality? They haven't launched any >13B model yet, although they plan to.

[ Parent | on HN ]

Re:Code Llama, a state-of-the-art large language model for c... by MaKey on Thursday August 24, 2023 @04:32PM (#37254178)

Oobabooga exposes an API.

[ Parent | on HN ]

Re:Code Llama, a state-of-the-art large language model for c... by BoorishBears on Thursday August 24, 2023 @04:14PM (#37253972)

I'm not into open source LLMs in the slightest, and yet even I've trivially found tools to do what both you and the poster above you wanted

lmstudio actually does what both of you want: provides an easy GUI and serves up your model over a local endpoint that mirrors the OpenAI API.

There's just too much noise in terms of the tooling for LLMs, the solution is fewer higher quality solutions, not more solutions

[ Parent | on HN ]

Re:Code Llama, a state-of-the-art large language model for c... by xanderatallah on Thursday August 24, 2023 @04:50PM (#37254370)

We’re trying to do this at https://openrouter.ai

[ Parent | on HN ]