google-research
haystack
Our great sponsors
google-research | haystack | |
---|---|---|
98 | 54 | |
32,804 | 13,633 | |
1.5% | 5.8% | |
9.6 | 9.9 | |
2 days ago | about 24 hours ago | |
Jupyter Notebook | Python | |
Apache License 2.0 | Apache License 2.0 |
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.
google-research
-
Show HN: Next-token prediction in JavaScript – build fast LLMs from scratch
People on here will be happy to say that I do a similar thing, however my sequence length is dynamic because I also use a 2nd data structure - I'll use pretentious academic speak: I use a simple bigram LM (2-gram) for single next-word likeliness and separately a trie that models all words and phrases (so, n-gram). Not sure how many total nodes because sentence lengths vary in training data, but there are about 200,000 entry points (keys) so probably about 2-10 million total nodes in the default setup.
"Constructing 7-gram LM": They likely started with bigrams (what I use) which only tells you the next word based on 1 word given, and thought to increase accuracy by modeling out more words in a sequence, and eventually let the user (developer) pass in any amount they want to model (https://github.com/google-research/google-research/blob/5c87...). I thought of this too at first, but I actually got more accuracy (and speed) out of just keeping them as bigrams and making a totally separate structure that models out an n-gram of all phrases (e.g. could be a 24-token long sequence or 100+ tokens etc. I model it all) and if that phrase is found, then I just get the bigram assumption of the last token of the phrase. This works better when the training data is more diverse (for a very generic model), but theirs would probably outperform mine on accuracy when the training data has a lot of nearly identical sentences that only change wildly toward the end - I don't find this pattern in typical data though, maybe for certain coding and other tasks there are those patterns though. But because it's not dynamic and they make you provide that number, even a low number (any phrase longer than 2 words) - theirs will always have to do more lookup work than with simple bigrams and they're also limited by that fixed number as far as accuracy. I wonder how scalable that is - if I need to train on occasional ~100-word long sentences but also (and mostly) just ~3-word long sentences, I guess I set this to 100 and have a mostly "undefined" trie.
I also thought of the name "LMJS", theirs is "jslm" :) but I went with simply "next-token-prediction" because that's what it ultimately does as a library. I don't know what theirs is really designed for other than proving a concept. Most of their code files are actually comments and hypothetical scenarios.
I recently added a browser example showing simple autocomplete using my library: https://github.com/bennyschmidt/next-token-prediction/tree/m... (video)
And next I'm implementing 8-dimensional embeddings that are converted to normalized vectors between 0-1 to see if doing math on them does anything useful beyond similarity, right now they look like this:
[nextFrequency, prevalence, specificity, length, firstLetter, lastLetter, firstVowel, lastVowel]
- Google Research website is down
-
Jpegli: A New JPEG Coding Library
The change was literally just made: https://github.com/google-research/google-research/commit/4a...
It appears this was in response to Hacker News comments.
- Multi-bitrate JPEG compression perceptual evaluation dataset 2023
-
Vector Databases: A Technical Primer [pdf]
There are options such as Google's ScaNN that may let you go farther before needing to consider specialized databases.
https://github.com/google-research/google-research/blob/mast...
-
Labs.Google
I feel it was unnecesary to create this because https://research.google/ already exists? It just seems like they want to take another URL with a "pure" domain name instead of psubdirectories, etc parts.
-
Smerf: Streamable Memory Efficient Radiance Fields
https://github.com/google-research/google-research/blob/mast...
-
Shisa 7B: a new JA/EN bilingual model based on Mistral 7B
You could also try some dedicated translation models like https://huggingface.co/facebook/nllb-moe-54b (or https://github.com/google-research/google-research/tree/master/madlad_400 for something smaller) and see how they do.
-
Translate to and from 400+ languages locally with MADLAD-400
Google released T5X checkpoints for MADLAD-400 a couple of months ago, but nobody could figure out how to run them. Turns out the vocabulary was wrong, but they uploaded the correct one last week.
- Mastering ROUGE Matrix: Your Guide to Large Language Model Evaluation for Summarization with Examples
haystack
-
Release Radar • March 2024 Edition
View on GitHub
-
First 15 Open Source Advent projects
4. Haystack by Deepset | Github | tutorial
-
Generative AI Frameworks and Tools Every Developer Should Know!
Haystack can be classified as an end-to-end framework for building applications powered by various NLP technologies, including but not limited to generative AI. While it doesn't directly focus on building generative models from scratch, it provides a robust platform for:
-
Best way to programmatically extract data from a set of .pdf files?
But if you want an API that you can use to develop your own flow, Haystack from Deepset could be worth a look.
-
Which LLM framework(s) do you use in production and why?
Haystack for production. We cannot afford breaking changes in our production apps. Its stable, documentation is excellent and did I mention its' STABLE!??
- Overview: AI Assembly Architectures
-
Llama2 and Haystack on Colab
I recently conducted some experiments with Llama2 and Haystack (https://github.com/deepset-ai/haystack), the NLP/LLM framework.
The notebook can be helpful for those trying to load Llama2 on Colab.
1) Installed Transformers from the main branch (and other libraries)
- Build with LLMs for production with Haystack – has 10k stars on GitHub
- Show HN: Haystack – Production-Ready LLM Framework
-
Langchain Is Pointless
there is an alternative that is production-grade - deepset haystack https://haystack.deepset.ai/
p.s. i am contributor so there could be bias
What are some alternatives?
qdrant - Qdrant - High-performance, massive-scale Vector Database for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/
langchain - 🦜🔗 Build context-aware reasoning applications
fast-soft-sort - Fast Differentiable Sorting and Ranking
langchain - ⚡ Building applications with LLMs through composability ⚡ [Moved to: https://github.com/langchain-ai/langchain]
faiss - A library for efficient similarity search and clustering of dense vectors.
gpt-neo - An implementation of model parallel GPT-2 and GPT-3-style models using the mesh-tensorflow library.
ml-agents - The Unity Machine Learning Agents Toolkit (ML-Agents) is an open-source project that enables games and simulations to serve as environments for training intelligent agents using deep reinforcement learning and imitation learning.
BentoML - The most flexible way to serve AI/ML models in production - Build Model Inference Service, LLM APIs, Inference Graph/Pipelines, Compound AI systems, Multi-Modal, RAG as a Service, and more!
Milvus - A cloud-native vector database, storage for next generation AI applications
label-studio - Label Studio is a multi-type data labeling and annotation tool with standardized output format
struct2depth - Models and examples built with TensorFlow
jina - ☁️ Build multimodal AI applications with cloud-native stack