smy20011

I tried to use Sakura LLM to translate some JP novels. It's really good and half the price of GPT3.5 turbo.

https://github.com/SakuraLLM/Sakura-13B-Galgame/tree/dev_ser...

You should at least have some basic ideas about your stack.

Thank you. I think most things we store in the config are non-business logic. Like the connection string of database or some feature flags.

However, the prompt is your business logic in most cases and put your business logic into a separate file make it harder to read and harder to maintain.

Why not store them in code? Easier to read and source controlled.

Other than coding, do we have a good application of LLMs?

The UI looks like ELK (https://github.com/elk-zone/elk/)

Only 20%? I think the numbers are close to 80%.

Cannot see anything. Do I need to login?

People getting rate limited message cannot see that due to rate limit.

It's fine that website down. How can it down 3 hrs? Where are the engineers?

racism against white That's really rare. More like "I don't like lossing my privilege"

I don't think so. Chat based interface is horrible on phone. You have to type what you want instead of tapping things.

Chatbot should be part of your ui instead of replacing the ui.

One thing AMD can do is working with ggml to make llama.cpp running on AMD GPUs. Compile modern ML framework is a quite complex due to number of OPs. However, running LLMs does not need a lot of OPs. Just einsum & relu & softmax. Having LLM works with llama.cpp could be done by a team within a week or so.

Why not just buying bonds?

My test query is "why LOLIN S3's LED is not working". All LLM failed on that query, this included.

We build web browser for a reason. Talk to a chatbot like talk to customer service. It's far slower and sometimes frustration.

It seems that OAI have their preference of choosing the first movers of their ecosystem.

But you can already do it for a long time.

Alpaca model leaked again?

Maybe out-dated by 1 day LOL.

2 AI winter so far!

Dude, 1M words cost $2. You charge $3 for what?

The 600t performance is with sparsity in the spec. I think the price is nearly break even if sparsity is not used in the model.

Some growth hacker newsletter starts with C.

Do you ask chatgpt to put as many buzzwords as possible?

How, could you elaborate?

Not OP, this is highly unethical.

TBF, I don't want my DB to be wiped if i remove one line of code.

I think you mixed UI code with platform channel code. The only code that use platform channel is this line.

https://github.com/flutter/flutter/blob/master/examples/plat...

I really hope flutter can provide a guide for FFI though.

For the steel, no, if you import more ores, you will get lower prices. The production costs will lower due to large scale production.