On gpu, processing the input prompt, even for huge prompts, is almost instant. Meaning, even if your prompt is huge, it will start generating new tokens after your prompt very quickly. On a rented A6000 gpu, using llama+lora 30b, you can use huge prompts and it will start giving a new output right away.

On cpu (i.e. the project llama.cpu), it takes a very, very long time to process the input prompt, before it begins to generate new tokens. Meaning, if you provide a huge copy/paste of code, it will take a long time to ingest all that input, before it begins outputting new tokens.

Once it finally starts outputting new tokens, the rate is surprisingly fast, not much slower than gpu.

I wish I knew the reason for this, but I'm not an expert :) I've just seen this in practice.

I’ve been using OpenAI API with chatblade and been giving it code in various languages and it’s quite surprising how well it describes the purpose and code implementation in english. The english description would be useful and relevant for developers trying to quickly familiarize themselves with a code base.

For a typical 400-600 line file it looks like it would cost around 1-3 cents per file. However loss of privacy isn’t so great.

How do you find output quality of llama + lora for such a task?

Code is research code I’d run it on.

Jokes aside, the limiting factor will be either a technique to pack all of the code into smaller tokens like semantic search (someone else will be able to comment on this as that's the limit of my understanding) or GPU memory for input tokens.

Buying a "high end GPU" isn't buying a 4090 or even two, it's 250k on a DGX unit and putting it in a datacentre. You will probably be able to find a service that would sign a confidentiality agreement and provide you with this service for less than 250k.

I haven't started to play with LLMs locally in anger yet, but I was under the impression that you could use a 4090 in combination with FlexGen to achieve this rather than having to buy special hardware?

But it is pretty cheap to rent something at vast.ai or whatever to get 40GB for a final run.

This is for inference, not training, and I’d do it on blocks of code with less than 4096 tokens. That’s what I have to do with gpt 3.5 turbo via api.

I can do what I want with the API and it is around 1-2 cents per batch of code I run through it, typically 400 lines of average code is around 4k tokens.

If you're trying to get codebase level introspection you might need to wait a bit for some of these techs to mature.

Exciting space and yea, learning heaps myself day by day.

In my opinion the code descriptions gpt 3.5 turbo has been spitting out for me are good quality and concise. I’d argue they are probably better than what many of the developers themselves would write, especially when english isn’t native for the developer.

Does anyone have a projection based on historical GPU cost reductions as to how long we have to wait until a DGX unit costs as little as a 4090 does today?

[0]https://github.com/THUDM/ChatGLM-6B/blob/main/README_en.md [1]https://huggingface.co/spaces/multimodalart/ChatGLM-6B

It seems like working on locally runnable LLM that has been fine tuned to focus on code should be a high priority.

That said, there are some summarisation tasks I prefer to run locally even given the massive drop in quality (e.g. using Alpaca), both for privacy reasons and to keep myself up-to-date on local LLMs.

P.S. I'm discounting older local summarisation-specific networks, I have found local LLMs to be a jump in quality over them

The answer will be pretty damn good , especially with gpt 4, but it’s still good with gpt 3.5 turbo. Try it out yourself with whatever code you have.

This english description of code can then be searched against. That’s the primary practical application I’m thinking about doing currently.