jsonformer
clownfish
jsonformer | clownfish | |
---|---|---|
25 | 11 | |
3,868 | 303 | |
- | - | |
5.4 | 4.3 | |
3 months ago | almost 1 year ago | |
Jupyter Notebook | Python | |
MIT License | 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
clownfish
-
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)
- OpenAI Function calling and API updates
-
Adding GPT to a web app. The real experience.
I can see some specific problems there, like malformed json (or json not matching intended schema being generated). Approaches like https://github.com/1rgs/jsonformer and https://github.com/newhouseb/clownfish could be interesting there, as well as approaches to validate outputs like https://medium.com/@markherhold/validating-json-patch-requests-44ca5981a7fc (references jsonpatch which could be interesting as well, but the approach is somewhat agnostic to how the changes actually get applied while still allowing you to enforce structure around what changes and how).
-
When you lose the ability to write, you also lose some of your ability to think
https://github.com/newhouseb/clownfish
Structural Alignment: Modifying Transformers (like GPT) to Follow a JSON Schema
- Clownfish: Constrained Decoding for LLMs Against JSON Schema
-
Jsonformer: A bulletproof way to generate structured output from LLMs
Oh nice! I built a similar system a few weeks ago: https://github.com/newhouseb/clownfish
I think the main differentiating factor here is that this is better if you have a simpler JSON schema without enums or oneOf constraints. If you do have these constraints, i.e. let's say you wanted an array of different types that represented a items on a menu { kind: pizza, toppings: [pepperoni] } or { kind: ice_cream, flavor: vanilla | strawberry } then you would need something more sophisticated like clownfish that can ask the LLM to pick specific properties.
-
Prompt injection: what’s the worst that can happen?
And on the other end, there's https://github.com/newhouseb/clownfish to force the model to produce structured output.
-
Teaching ChatGPT to Speak My Son’s Invented Language
It doesn't help with repetition, but when it comes to force structure on the output data, this approach looks interesting:
https://github.com/newhouseb/clownfish
TL;DR: it exploits the fact that the model returns probabilities for all the possible following tokens to enforce a JSON schema on the output as it is produced, backtracking as needed.
- Structural Alignment: Modifying Transformers (Like GPT) to Follow a JSON Schema
- Structural Alignment of LLMs with ControLogits
What are some alternatives?
mlc-llm - Enable everyone to develop, optimize and deploy AI models natively on everyone's devices.
lmql - A language for constraint-guided and efficient LLM programming.
aider - aider is AI pair programming in your terminal
outlines - Structured Text Generation
evals - Evals is a framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks.
gpt-json - Structured and typehinted GPT responses in Python
ChatGPT_DAN - ChatGPT DAN, Jailbreaks prompt
jikkou - The Open source Resource as Code framework for Apache Kafka
kodumisto - GitHub Issue as ChatGPT Prompt; ChatGPT's Response as a Pull Request
evadb - Database system for AI-powered apps
AICommand - ChatGPT integration with Unity Editor