lmql
jsonformer
lmql | jsonformer | |
---|---|---|
30 | 25 | |
3,342 | 3,793 | |
2.9% | - | |
9.5 | 5.4 | |
6 days ago | 2 months ago | |
Python | Jupyter Notebook | |
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.
lmql
- Show HN: Fructose, LLM calls as strongly typed functions
-
Prompting LLMs to constrain output
have been experimenting with guidance and lmql. a bit too early to give any well formed opinions but really do like the idea of constraining llm output.
-
[D] Prompt Engineering Seems Like Guesswork - How To Evaluate LLM Application Properly?
the only time i've ever felt like it was anything other than guesswork was using LMQL . not coincidentally, LMQL works with LLMs as autocomplete engines rather than q&a ones.
-
Guidance for selecting a function-calling library?
lqml
-
Show HN: Magentic – Use LLMs as simple Python functions
This is also similar in spirit to LMQL
https://github.com/eth-sri/lmql
- Show HN: LLMs can generate valid JSON 100% of the time
- LangChain Agent Simulation – Multi-Player Dungeons and Dragons
-
The Problem with LangChain
LLM calls are just function calls, so most functional composition is already afforded by any general-purpose language out there. If you need fancy stuff, use something like Python‘s functools.
Working on https://github.com/eth-sri/lmql (shameless plug, sorry), we have always found that compositional abstractions on top of LMQL are mostly there already, once you internalize prompts being functions.
- Is there a UI that can limit LLM tokens to a preset list?
-
Local LLMs: After Novelty Wanes
LMQL is another.
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
What are some alternatives?
guidance - A guidance language for controlling large language models.
mlc-llm - Enable everyone to develop, optimize and deploy AI models natively on everyone's devices.
guidance - A guidance language for controlling large language models. [Moved to: https://github.com/guidance-ai/guidance]
aider - aider is AI pair programming in your terminal
simpleaichat - Python package for easily interfacing with chat apps, with robust features and minimal code complexity.
clownfish - Constrained Decoding for LLMs against JSON Schema
NeMo-Guardrails - NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.
outlines - Structured Text Generation
guardrails - Adding guardrails to large language models.
gpt-json - Structured and typehinted GPT responses in Python
basaran - Basaran is an open-source alternative to the OpenAI text completion API. It provides a compatible streaming API for your Hugging Face Transformers-based text generation models.
jikkou - The Open source Resource as Code framework for Apache Kafka