LLM Reference

airoboros L2 70B 2.2.1

About

The Airoboros L2 70B 2.2.1, built on the Llama 2 architecture, is a large language model optimized for instruction following rather than casual conversation. With 70 billion parameters, it excels in tasks like instruction following, question answering, summarization, and coding. The model employs a unique prompting format, A chat.\nUSER: {prompt}\nASSISTANT:, and benefits from using explicit delimiters to reduce hallucinations in closed-context instructions. A limitation is that Q4_0 quantization yields unusable outputs. Additionally, the model uses a substantial amount of synthetic data generated by the Airoboros tool, and its licensing remains ambiguous, potentially restricting commercial use due to OpenAI's GPT-4 API involvement in data generation.

Capabilities

MultimodalFunction CallingTool UseJSON Mode

Providers(1)

ProviderInput (per 1M)Output (per 1M)Type
deepinfra API
Serverless

Specifications

Familyairoboros
Parameters70B
ArchitectureDecoder Only
Specializationgeneral