sentencepiece
langchain
Our great sponsors
sentencepiece | langchain | |
---|---|---|
19 | 31 | |
9,480 | 83,220 | |
4.6% | 6.5% | |
8.1 | 10.0 | |
16 days ago | 4 days ago | |
C++ | Python | |
Apache License 2.0 | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
sentencepiece
- sentencepiece
-
LLM.int8(): 8-Bit Matrix Multiplication for Transformers at Scale
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
-
[P] TokenMonster Ungreedy ~ 35% faster inference and 35% increased context-length for large language models (compared to tiktoken). Benchmarks included.
a) Comparison with SentencePiece tokenizer with comparable settings (It can also ignore word-boundaries and create phrase tokens)
-
LLaMA tokenizer: is a JavaScript implementation available anywhere?
LLaMA uses the sentencepiece tokenizer: https://github.com/google/sentencepiece
-
[P] New tokenization method improves LLM performance & context-length by 25%+
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).
-
Code runs without definition of function (automatically calls a different function instead)
Hi, I'm studying the implementation of encode and decode functions for Google's SentencePiece tokenizer.
-
How to handle multiple languages in a sentence?
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
- Large language models are having their Stable Diffusion moment
-
LLaMA-7B in Pure C++ with full Apple Silicon support
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.
- ChatGPT in an iOS Shortcut – Worlds Smartest HomeKit Voice Assistant
langchain
-
Aider: AI pair programming in your terminal
Big fan of Aider.
We are interesting in integrating Aider as a tool for Dosu https://dosu.dev/ to help it navigate and modify a codebase on issues like this https://github.com/langchain-ai/langchain/issues/8263#issuec...
-
🦙 Llama-2-GGML-CSV-Chatbot 🤖
Developed using Langchain and Streamlit technologies for enhanced performance.
-
Building a WhatsApp generative AI assistant with Amazon Bedrock and Python
Tip: Kenton Blacutt, an AWS Associate Cloud App Developer, collaborated with Langchain, creating the Amazon Dynamodb based memory class that allows us to store the history of a langchain agent in an Amazon DynamoDB.
-
👑 Top Open Source Projects of 2023 🚀
LangChain was first released in October 2022 as an open-source side project, a framework that makes developing AI applications more flexible. It got so popular that it was promptly turned into a startup.
-
Fuck You, Show Me the Prompt
> Furthermore, the prompt has a spelling error (Let'w) and also overly focuses on the negative about identifying errors - which makes me skeptical that this prompt has been optimized or tested.
Fixed in https://github.com/langchain-ai/langchain/commit/7c6009b76f0...
- LangChain Repository Disappeared
-
🆓 Local & Open Source AI: a kind ollama & LlamaIndex intro
Being able to plug third party frameworks (Langchain, LlamaIndex) so you can build complex projects
-
Easy Guide to Creating Smart Chatbots with Langchain & GPT-4
Access Langchain's repository at Langchain's Repository.
- Use WASM as a cross-platform LLM back end for LangChain: any LLMs on any device
-
Llamafile lets you distribute and run LLMs with a single file
This comment is now a potential exploit for any such system that encounters it (in practice most won't be fooled by trivial prompt injections, but possibly more complex ones)
Here's one example I found with a quick search: https://github.com/langchain-ai/langchain/issues/5872
What are some alternatives?
transformers - 🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
llama_index - LlamaIndex is a data framework for your LLM applications
CTranslate2 - Fast inference engine for Transformer models
semantic-kernel - Integrate cutting-edge LLM technology quickly and easily into your apps
llama - Inference code for Llama models
haystack - :mag: LLM orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data. With advanced retrieval methods, it's best suited for building RAG, question answering, semantic search or conversational agent chatbots.
gpt-2 - Code for the paper "Language Models are Unsupervised Multitask Learners"
griptape - Modular Python framework for AI agents and workflows with chain-of-thought reasoning, tools, and memory.
text-generation-webui - A Gradio web UI for Large Language Models. Supports transformers, GPTQ, AWQ, EXL2, llama.cpp (GGUF), Llama models.
OpenNMT-Tutorial - Neural Machine Translation (NMT) tutorial. Data preprocessing, model training, evaluation, and deployment.
private-gpt - Interact with your documents using the power of GPT, 100% privately, no data leaks