Constrained-Text-Generation-Studio
relm
Constrained-Text-Generation-Studio | relm | |
---|---|---|
25 | 3 | |
197 | 89 | |
- | - | |
4.1 | 5.1 | |
9 months ago | 12 months ago | |
Python | Python | |
MIT License | 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.
Constrained-Text-Generation-Studio
-
Photoshop for Text (2022)
Oh my god. I wrote a whole library called "Constrained Text Generation Studio" where I mused that I wanted a "Photoshop for Text". I'm not even sure which work predates the other: https://github.com/Hellisotherpeople/Constrained-Text-Genera...
The core idea of a "photoshop for text", specifically a word processor made for prosumers supporting GenAI first class (i.e oobabooga but actually good) - is worth so much. If you're a VC reading this, chances are I want to talk to you to actually execute on the idea from the OP
-
Ask HN: What have you built with LLMs?
I was working on this stuff before it was cool, so in the sense of the precursor to LLMs (and sometimes supporting LLMs still) I've built many things:
1. Games you can play with word2vec or related models (could be drop in replaced with sentence transformer). It's crazy that this is 5 years old now: https://github.com/Hellisotherpeople/Language-games
2. "Constrained Text Generation Studio" - A research project I wrote when I was trying to solve LLM's inability to follow syntactic, phonetic, or semantic constraints: https://github.com/Hellisotherpeople/Constrained-Text-Genera...
3. DebateKG - A bunch of "Semantic Knowledge Graphs" built on my pet debate evidence dataset (LLM backed embeddings indexes synchronized with a graphDB and a sqlDB via txtai). Can create compelling policy debate cases https://github.com/Hellisotherpeople/DebateKG
4. My failed attempt at a good extractive summarizer. My life work is dedicated to one day solving the problems I tried to fix with this project: https://github.com/Hellisotherpeople/CX_DB8
-
You need a mental model of LLMs to build or use a LLM-based product
My mental model for LLMs was built by carefully studying the distribution of its output vocabulary at every time step.
There are tools that allow you to right click and see all possible continuations for an LLM like you would in a code IDE[1]. Seeing what this vocabulary is[2] and how trivial modifications to the prompt can impact probabilities will do a lot for improving the mental model of how LLM operate.
Shameless self plug, but software which can do what I am describing is here, and it's worth noting that it ended up as peer reviewed research.
[1] https://github.com/Hellisotherpeople/Constrained-Text-Genera...
-
Ask HN: How training of LLM dedicated to code is different from LLM of “text”
Yeah, the LLM outputs a distribution of likely next tokens. It is up to the decoder to select one, and it can use a grammar to enforce certain rules on the output. https://github.com/Hellisotherpeople/Constrained-Text-Genera... or https://github.com/ggerganov/llama.cpp/blob/master/grammars/... for example.
- Show HN: LLMs can generate valid JSON 100% of the time
-
Llama: Add Grammar-Based Sampling
I am in love with this, I tried my hand at building a Constrained Text Generation Studio (https://github.com/Hellisotherpeople/Constrained-Text-Genera...), and got published at COLING 2022 for my paper on it (https://paperswithcode.com/paper/most-language-models-can-be...), but I always knew that something like this or the related idea enumerated in this paper: https://arxiv.org/abs/2306.03081 was the way to go.
-
LLMs are too easy to automatically red team into toxicity
It's far too easy to destroy any type of RLHF done to try to prevent bad behavior from an LLM.
For example, if you want a LLM to generate things that look like social security numbers, you may try to prompt it asking for social security numbers. It will of course give you "I'm sorry hal I can't do that..."
Then start using a technique like token filtering/filter assisted decoding, to make it where the LLM can only generate hyphens and numbers, and suddenly it does what you ask despite RLHF
I explored this a tiny bit in the later sections of my paper studying what happens when you restrict an LLMs vocabulary: https://aclanthology.org/2022.cai-1.pdf#page=17
You can even play with this with open source models using CTGS: https://github.com/Hellisotherpeople/Constrained-Text-Genera...
-
Understanding GPT Tokenizers
I agree with you, and I'm SHOCKED at how little work there actually is in phonetics within the NLP community. Consider that most of the phonetic tools that I am using to enforce rhyming or similar syntactic constrained in constrained text generation studio (https://github.com/Hellisotherpeople/Constrained-Text-Genera...) were built circa 2014, such as the CMU rhyming dictionary. In most cases, I could not find better modern implementations of these tools.
I did learn an awful lot about phonetic representations and matching algorithms. Things like "soundex" and "double metaphone" now make sense to me and are fascinating to read about.
-
Don Knuth Plays with ChatGPT
https://github.com/hellisotherpeople/constrained-text-genera...
Just ban the damn tokens and try again. I wish that folks had more intuition around tokenization, and why LLMs struggle to follow syntactic, lexical, or phonetic constraints.
- Constrained Text Generation Studio
relm
-
Show HN: LLMs can generate valid JSON 100% of the time
I'm not sure how this is different than:
https://github.com/1rgs/jsonformer
or
https://github.com/newhouseb/clownfish
or
https://github.com/mkuchnik/relm
or
https://github.com/ggerganov/llama.cpp/pull/1773
or
https://github.com/Shopify/torch-grammar
Overall there are a ton of these logit based guidance systems, the reason they don't get tons of traction is the SOTA models are behind REST APIs that don't enable this fine-grained approach.
Those models perform so much better that people generally settle for just re-requesting until they get the correct format (and with GPT-4 that ends up being a fairly rare occurrence in my experience)
-
CMU Researchers Introduce ReLM: An AI System For Validating And Querying LLMs Using Standard Regular Expressions
Github: https://github.com/mkuchnik/relm
-
Jsonformer: A bulletproof way to generate structured output from LLMs
I have stumbled upon your repository a week ago and I have to say, great work and great ideas!
Another thing I thought about is integrating formatting for fields using a similar system. ISO-8601 dates comes immediately to mind but also number and currency formatting are other examples.
Probabilistic enums is another thing that I can think of that might be useful for fallback values, I am pretty sure there's a lot of work that can be done in this area, also for other parser kinds
related and highly recommended resource is https://github.com/mkuchnik/relm and https://arxiv.org/abs/2211.15458. It is a similar system used to validate LLMs using regexes, however built for completely different use cases. I imagine integrating regex checks to the output fields can also have a lot of use cases.
What are some alternatives?
Constrained-Text-Genera
jsonformer - A Bulletproof Way to Generate Structured JSON from Language Models
guidance - A guidance language for controlling large language models.
torch-grammar
agency - Agency: Robust LLM Agent Management with Go
llm-mlc - LLM plugin for running models using MLC
llama-tokenizer-js - JS tokenizer for LLaMA and LLaMA 2
outlines - Structured Text Generation
Chat-Markup-Language - This is a Repo defining a set of rules for ChatGPT to use when sending responses to a user