sentencepiece VS langchain

you need to train the model on 1 trillion tokens (https://platform.openai.com/tokenizer https://github.com/google/sentencepiece) anyways for it to get reasoning capacities, which it feels very unlikely that your data is that much.

I'm highly skeptical that you have enough data to pretrain if you don't have enough data to fine tune.

fine tuning + vector search + prompting of as much stuff as you can, on a LLM like palm2 or gpt4 is what I would do. otherwise you can use falcon 40B ofc.

maybe I should charge for this ahah

a) Comparison with SentencePiece tokenizer with comparable settings (It can also ignore word-boundaries and create phrase tokens)

LLaMA uses the sentencepiece tokenizer: https://github.com/google/sentencepiece

Besides, are you familiar with SentencePiece? What you are doing looks very similar (generate a large vocab, prune worst token until vocab size is reached), only the token selection criterion is different. It's also purely data driven in the sense that there are no assumption specific to language (and it can optionally segment across whitespace, as you are doing).

Hi, I'm studying the implementation of encode and decode functions for Google's SentencePiece tokenizer.

I think many LMs nowadays use unicode tokenizers, that are not tied to specific languages. E.g. sentencepiece is the most popular one: https://github.com/google/sentencepiece

If you are interested in implementing LLaMA yourself or learning, I noticed that the reference code by Facebook is one of the cleaner, easier to read ML code I've seen in a while. https://github.com/facebookresearch/llama/blob/main/llama/mo... It's about 200 lines long. You probably do need a bit of knowledge to understand what you are reading but I was pleasantly surprised.

For example in comparison, StableDiffusion torch code in diffusers and transformers Python libraries has lots of conditionals, experiments etc. that are not being used that can make it hard to follow what is going on.

Last weekend I got the "main loop" of the transformer working in pure CPU Rust code, following the reference code. My crappy code is just very very slow as I focused on getting it to run, not making it fast. The tokenizer uses some Google thing https://github.com/google/sentencepiece but luckily for inference it seems that you just need to be able to parse the tokenizer model file and not understand how it was created; I was able to strip out the protobuf files from that repository and add it to Rust and read the tokens.

I am optimistic that someone makes a high quality CPU or some CPU+GPU+SSD combination thingmaling that will make it somewhat practical to run even the large LLM models without needing an A100 or two.

Langchain and the implementation of Custom Tools also is a great (and very efficient) way to setup a dedicated Q&A (for example for chat purpose) agent.

We're using it via langchain talking to Amazon Bedrock which is hosting Claude 1.x. It's comparable to GPT3.x, not bad. The integration doesn't seem to be fully there though, I think langchain is expecting "Human:" and "AI:", but Claude uses "Assistant:".

https://github.com/hwchase17/langchain/issues/2638

Depending on how much work you want to put into it, you can get started at HuggingFace with their models and datasets, but you'd need compute power, multiple MLOps, etc. I was introduced to the concept in this video, since Google has their Vertex AI tools on Google Cloud, and there's always LangChain but I'm not sure about anything recent.

a documentation chatbot proof of concept using GPT3.5 and LangChain

I encourage everyone to pay attention to the Langchain open-source project and leverage it to achieve tasks that ChatGPT cannot handle.

Yeah I never know where memory goes exactly in langchain, it's not exactly clear all the time. But sure, the main insight I remember is this, take a look at their MULTI_PROMPT_ROUTER_TEMPLATE: https://github.com/hwchase17/langchain/blob/560c4dfc98287da1...

It's a lot of instructions for an LLM, they seem to forget an LLM is an auto-completion machine, and which data it is trained on. Using <<>> for sections is not a normal thing, it's not markdown, which probably the thing read way more often on the internet, instead of open json comments, why not type signatures, instead of so many rules, why not give it examples? It is an autocomplete machine!

They are relying too much on the LLM being smart because they probably only test stuff in GPT-4 and 3.5, but with GPT4All models this prompt was not working at all, so I had to rewrite it, for simple routing, we don't even need json, carying the `next_inputs` here is weird if you don't need it.

So this is my version of it: https://gist.github.com/rogeriochaves/b67676977eebb1936b9b5c...

It's so basic it's dumb, yet it is more powerful, as it does not rely on GPT-4 level intelligence, it's just what I needed