Inference
Inference is the process of running a trained machine learning model on new input data to produce a prediction, classification, or generated output. It is distinct from training, which is the earlier phase where the model learns its parameters from data; inference uses those already-learned, fixed parameters to…
11 resources across 3 libraries
Glossary Terms(5)
Context Window
The context window is the maximum amount of text, measured in tokens, that a language model can process and 'see' at one time, encompassing both the input prom…
Inference
Inference is the process of running a trained machine learning model on new input data to produce a prediction, classification, or generated output. It is dist…
Modal
Modal is a serverless cloud platform that lets developers run Python functions, including GPU-backed AI workloads, in the cloud without managing servers, conta…
Groq
Groq is an AI infrastructure company known for its custom LPU (Language Processing Unit) chips and GroqCloud API, which deliver very low-latency inference for…
Gemini Flash
Gemini Flash is the fast, cost-efficient tier of Google DeepMind's Gemini model family, optimized for high-throughput and latency-sensitive applications while…
Study Notes(5)
F# Syntax Basics
A tour of F#'s significant whitespace, function definitions, the pipe and composition operators, and basic types.
Type Inference in F#
See how F#'s Hindley-Milner-based type inference deduces precise types without annotations, and when explicit annotations are still needed.
Type Inference in Haskell
How GHC deduces the most general type of an expression without explicit annotations, using unification, and where the Monomorphism Restriction and ambiguous ty…
Type Inference in TypeScript
How TypeScript figures out types automatically from values, without explicit annotations.
Type Inference and Conversion in Swift
Learn how Swift infers types from literal values and why converting between types always requires an explicit initializer call.