jsonformer
pydantic-chatcompletion
jsonformer | pydantic-chatcompletion | |
---|---|---|
25 | 4 | |
3,868 | 52 | |
- | - | |
5.4 | 4.2 | |
3 months ago | 12 months ago | |
Jupyter Notebook | Python | |
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.
jsonformer
- Forcing AI to Follow a Specific Answer Pattern Using GBNF Grammar
-
Refact LLM: New 1.6B code model reaches 32% HumanEval and is SOTA for the size
- Tools like jsonformer https://github.com/1rgs/jsonformer are not possible with OpenAIs API.
-
Show HN: LLMs can generate valid JSON 100% of the time
How does this compare in terms of latency, cost, and effectiveness to jsonformer? https://github.com/1rgs/jsonformer
-
Ask HN: Explain how size of input changes ChatGPT performance
You're correct with interpreting how the model works wrt it returning tokens one at a time. The model returns one token, and the entire context window gets shifted right by one to for account it when generating the next one.
As for model performance at different context sizes, it's seems a bit complicated. From what I understand, even if models are tweaked (for example using the superHOT RoPE hack or sparse attention) to be able to use longer contexts, they still have to be fined tuned on input of this increased context to actually utilize it, but performance seems to degrade regardless as input length increases.
For your question about fine tuning models to respond with only "yes" or "no", I recommend looking into how the jsonformers library works: https://github.com/1rgs/jsonformer . Essentially, you still let the model generate many tokens for the next position, and only accept the ones that satisfy certain criteria (such as the token for "yes" and the token for "no".
You can do this with openAI API too, using tiktoken https://twitter.com/AAAzzam/status/1669753722828730378?t=d_W... . Be careful though as results will be different on different selections of tokens, as "YES", "Yes", "yes", etc are all different tokens to the best of my knowledge
- A framework to securely use LLMs in companies – Part 1: Overview of Risks
-
LLMs for Schema Augmentation
From here, we just need to continue generating tokens until we get to a closing quote. This approach was borrowed from Jsonformer which uses a similar approach to induce LLMs to generate structured output. Continuing to do so for each property using Replit's code LLM gives the following output:
-
Doesn't a 4090 massively overpower a 3090 for running local LLMs?
https://github.com/1rgs/jsonformer or https://github.com/microsoft/guidance may help get better results, but I ended up with a bit more of a custom solution.
-
“Sam altman won't tell you that GPT-4 has 220B parameters and is 16-way mixture model with 8 sets of weights”
I think function calling is just JSONformer idk: https://github.com/1rgs/jsonformer
- Inference Speed vs. Quality Hacks?
-
Best bet for parseable output?
jsonformer: https://github.com/1rgs/jsonformer
pydantic-chatcompletion
-
Show HN: Structed LLM outputs via Pydantic with struct-GPT
Hey everyone,
So, I stumbled upon this really cool idea of using Pydantic to deserialize and validate OpenAI's outputs over on this HN thread https://news.ycombinator.com/item?id=35821748.
It got me thinking about how I'd like a slightly tweaked API to better fit my own needs. I also found some neat stuff in jiggy-ai's Pydantic implementation for chat completion https://github.com/jiggy-ai/pydantic-chatcompletion/blob/mas..., and picked up tips from various blog posts and comments on how to up the game with the quality of a model's output by providing examples.
So, I cooked up this library - just about 200 lines of code, but it's got some nice features and it's fully tested. I hope some of you find it useful.
I'd love to hear your thoughts and feedback. Cheers!
-
GPT-JSON: Structured and typehinted GPT responses in Python
Nice project! I took some inspiration from this as well as https://github.com/jiggy-ai/pydantic-chatcompletion/blob/mas... to create the following:
https://github.com/knowsuchagency/struct-gpt
I tried to make the API as intuitive as possible and added the ability to provide examples to improve the reliability and quality of the LLM's output.
- Show HN: Easy data extraction from text with Pydantic and OpenAI
What are some alternatives?
mlc-llm - Enable everyone to develop, optimize and deploy AI models natively on everyone's devices.
gpt-json - Structured and typehinted GPT responses in Python
aider - aider is AI pair programming in your terminal
gpt-logic - Translate the natural language generated by OpenAI's GPT models or any other large language models into JavaScript data types like booleans and objects.
clownfish - Constrained Decoding for LLMs against JSON Schema
struct-gpt - get structured output from LLM's
outlines - Structured Text Generation
jikkou - The Open source Resource as Code framework for Apache Kafka
evadb - Database system for AI-powered apps
frogmouth - A Markdown browser for your terminal
Chat-Markup-Language - This is a Repo defining a set of rules for ChatGPT to use when sending responses to a user