tinyllama:latest

Upstream reference: TinyLlama 1.1B Chat v1.0

Publisher: TinyLlama project

TinyLlama documents a compact text model using the Llama 2 architecture and tokenizer, with this chat release further tuned on synthetic dialogues and preference data.

Publisher-described context, separate from Sigma5C observations and recorded catalog statistics.

Published upstream specifications

Parameters
1.1 billion Source
Chat-tuning stages
Dialogue fine-tuning followed by preference optimization Source
Upstream license label
Apache-2.0 Source

Publisher-described uses

  • Small conversational text models and language-model research. Source

Reference limitations

  • Using a Llama-compatible architecture does not make TinyLlama a Meta-authored checkpoint. A latest alias does not verify this v1.0 artifact. Source

A recorded tag and an upstream card association do not verify the deployed checkpoint, quantization, configured context or current hosted availability.

Publisher sources

Links

Recorded references do not establish downloadable weights, licensing or current availability.

1.1B
parameters
Q4_0
quantization
llama
architecture
2048
context
apache-2.0
license
2023-12-30
released

Where tinyllama:latest comes from

Company / lab

TinyLlama project

See every model and family from this maker.

Model family

tinyllama

Other versions and sizes in this line.

completion

Named in 1 observation page

Browse the Observatory

AI-generated & AI-scored. Every observation on this site is produced and judged by AI, and AI makes mistakes. Treat each result as a recorded observation under a declared protocol, as of its date. Method and marker legend