LLM Reference

Yi Large

About

Yi Large, developed by 01.AI, is a cutting-edge large language model (LLM) that excels in natural language processing tasks. Built on a transformer architecture, it is specifically fine-tuned for high efficiency and performance. Yi Large features a substantial 32k context window and is trained on an expansive 3 trillion-token multilingual dataset, mainly emphasizing English and Chinese. Its capabilities range from knowledge search and data classification to generating human-like chatbot conversations and providing customer service. Despite its superior performance across various benchmarks, Yi Large faces limitations such as slower output speeds and potential hallucinations. The model is competitively priced at $2 per million tokens and allows for fine-tuning to suit specific application needs 123457810.

Capabilities

MultimodalFunction CallingTool UseJSON Mode

Providers(2)

ProviderInput (per 1M)Output (per 1M)Type
Fireworks AI Platform
Provisioned
NVIDIA NIM
Provisioned

Specifications

FamilyYi
Released2024-05-13
Context32K
ArchitectureDecoder Only
Specializationgeneral