yeesian
Esmeralda
Coding Patterns – The CP-SAT Primer
A Strengthened Implementation of CuPDLP for Linear Programming by C Language
Understanding the Decline of Impact Factors in Informs Journals
Towards Large Language Models as Copilots for Theorem Proving in Lean
Exploring the Limits of Transfer Learning with a Unified Transformer (2019)
How do I get started with Jax on TPU VMs
Linearity of Relation Decoding in Transformer Language Models
LLM Evaluation: Everything You Need to Run, Benchmark Evals
Speech and Language Processing (3rd ed. draft)
The Greatest Meme Template
Coalescence: Making LLM inference 5x faster
Fast JSON Decoding for Local LLMs with Compressed Finite State Machine
Generative Uncertainty
My Life as a Con Man (2020)
Using llama-cpp-Python grammars to generate JSON
Re:OpenFst Python Extension
on Wednesday November 01, 2023 @06:26AM (#38096531)
FST implementation in Rust: https://news.ycombinator.com/item?id=38096511
Re:Finite-State Transducers in Language and Speech Processing (1997)
on Wednesday November 01, 2023 @06:24AM (#38096519)
Relatedly (from a data structures perspective): https://news.ycombinator.com/item?id=10551280
Finite-State Transducers in Language and Speech Processing (1997)
Finite-State Transducer
OpenFst Python Extension
Chevrotain: Parser Building Toolkit for JavaScript
Re:Peg Parsers (2019)
on Tuesday October 31, 2023 @06:29AM (#38082642)
This was posted in the past (https://news.ycombinator.com/item?id=20502032); just re-posting now in light of their potential application to LLM grammars (https://news.ycombinator.com/item?id=38082219 for context)
Peg Parsers (2019)
Ohm: A library and language for building parsers, interpreters, compilers, etc.
Re:Grammar Prompting for Domain-Specific Language Generation with LLMs
on Tuesday October 31, 2023 @05:35AM (#38082219)
Relatedly:
Llama: Add grammar-based sampling - https://news.ycombinator.com/item?id=36819906 (105 comments)
ReLLM: Exact Structure for Large Language Model Completions - https://news.ycombinator.com/item?id=35829399 (13 comments)
Show HN: Structured output from LLMs without reprompting - https://news.ycombinator.com/item?id=36750083 (54 comments)
Show HN: LLMs can generate valid JSON 100% of the time - https://news.ycombinator.com/item?id=37125118 (303 comments)
A guidance language for controlling LLMs - https://news.ycombinator.com/item?id=35963936 (190 comments)
Grammar Prompting for Domain-Specific Language Generation with LLMs
Re:Alternate Hard and Soft Layers
on Tuesday October 31, 2023 @05:15AM (#38082072)