Blogs
Code Generation with Large Language Models - Fireworks Take
“Programming is the art of telling another human being what one wants the computer to do. We should continually strive to transform every art into a science: in the process, we advance the art” - Donald Knuth in Art of Programming.
BlogsUnlock Advanced Reasoning with NVIDIA Nemotron Nano 2 Models on FireworksFireworks
BlogsHow we fixed prompt injection for all models on FireworksFireworks
BlogsTrilogy Validates Open-Weight AI Models for Enterprise Workloads with FireworksFireworks
BlogsFrom text to task: Constrained generation for structured extraction in R1Fireworks
BlogsAnnouncing custom models and on-demand H100s with 50%+ lower costs and latency than vLLMFireworks
BlogsReinforcement Fine Tuning: Train expert open models to surpass closed frontier modelsFireworks
BlogsRethinking Snapshots at Scale: Neon vs AWS RDS - NeonNeon
BlogsJust landed in the Neon CLI - NeonNeon
Products & ServicesSpeech Understanding APIAssemblyai
Products & ServicesPre-recorded Speech-to-Text API | AssemblyAIAssemblyai
ResourcesIssue propertiesLinear
ResearchCritical Learning Periods: Leveraging Early training Dynamics for Efficient Data PruningCohere
ResearchThe Art of Asking: Multilingual Prompt Optimization for Synthetic DataCohere
Products & ServicesModel Vault | Dedicated Model Inference Platform | CohereCohere
ResearchBAM! Just Like That: Simple and Efficient Parameter Upcycling for Mixture of ExpertsCohere
ResearchAdaptation Odyssey in LLMs: Why Does Additional Pretraining Sometimes Fail to Improve?Cohere
ResearchElo Uncovered: Robustness and Best Practices in Language Model EvaluationCohere
ResearchNo News is Good News: A Critique of the One Billion Word BenchmarkCohere
ResearchSnapKV: LLM Knows What You are Looking for Before GenerationCohere
ResearchFrom One to Many: Expanding the Scope of Toxicity Mitigation in Language ModelsCohere
