-
InfluxDB
Power Real-Time Data Analytics at Scale. Get real-time insights from all types of time series data with InfluxDB. Ingest, query, and analyze billions of data points in real-time with unbounded cardinality.
> Are you using a normal training script i.e. "continued pretraining" on ALL parameters with just document fragments rather than input output pairs?
Yes, this one.
> do you make a custom dataset that has qa pairs about that particular knowledgebase?
This one. Once you have a checkpoint w knowledge, it makes sense to finetune. You can use either LORA or PEFT. We do it depending on the case. (some orgs have like millions of tokens and i am not that confident that PEFT).
LoRA with raw document text may not work, haven't tried that. Google has a good example of training scripts here: https://github.com/google-research/t5x (under training. and then finetuning). I like this one. Facebook Research also has a few on their repo.
If you are just looking to scrape by, I would suggest just do what they tell you to do. You can offer suggestions, but better let them take the call. A lot of fluff, a lot of chatter online, so everyone is figuring out stuff.
One note about pretraining is that it is costly, so most OSS devs just do direct finetuning/LoRA. Works because their dataset is from the open internet. Orgs aren't finding much value with these. And yet, many communities are filled with these tactics.
https://github.com/ggerganov/llama.cpp/pull/4406
The GGUF handling for Mistral's mixture of experts hasn't been finalized yet. TheBloke and ggerganov and friends are still figuring out what works best.
The Q5_K_M gguf model is about 32GB. That's not going to fit into any consumer grade GPU, but it should be possible to run on a reasonably powerful workstation or gaming rig. Maybe not fast enough to be useful for everyday productivity, but it should run well enough to get a sense of what's possible. Sort of a glimpse into the future.
I agree with you, stavros. There is no transfer between C coding and ML topics. However the original question is a bit more in the business side IMHO. Anyway: I've some experience with machine learning: 20 years ago I wrote (my first neural network)[https://github.com/antirez/nn-2003] and since then I always stayed in the loop. Not for work, as I specialized in system programming, but for personal research I played with NN images compression, NLP tasks and convnets. In more recent times I use pytorch for my stuff, LLM fine-tuning and I'm a "local LLMs" enthusiast. I speculated a lot about AI, and wrote a novel about this topic. So while the question was more in the business side, I have some competence in the general field of ML.