AI models
GPT2+CoreLM+Fine-Tuning
Training compute
1.2×10²⁰ FLOP
Parameters
132M
Published
Nov 4, 2021
GPT2+CoreLM+Fine-Tuning is an AI model developed by Aristotle University of Thessaloniki (Greece), first published in November 2021. It works in the language domain, on tasks such as language modeling/generation and named entity recognition (ner).
Training it took an estimated 1.2×10²⁰ FLOP of compute (estimation method: hardware). The model has 132,000,000 parameters. Training ran on 1 NVIDIA Titan V for about 8 hours.
Access: Unreleased. Its weights are not openly released. It is built on top of GPT-2 (124M). The reference paper has 2 citations. Epoch AI rates the confidence of this record as likely.
Full record
- Organization
- Aristotle University of Thessaloniki
- Country of organization
- Greece
- Domain
- Language
- Task
- Language modeling/generation, Named entity recognition (NER)
- Training compute
- 1.2×10²⁰ FLOP
- Compute estimation method
- Hardware
- Parameters
- 132,000,000
- Training hardware
- NVIDIA Titan V
- Chips used
- 1
- Training time
- 8 h
- Training power draw
- 277 W
- Numerical format
- FP16
- Model accessibility
- Unreleased
- Open weights
- No
- Base model
- GPT-2 (124M)
- Citations
- 2
- Epoch confidence
- Likely
SourceEpoch AI, 'AI Models'. Published online at epoch.ai. Retrieved 2026-07-29 from https://epoch.ai/data/ai-models. Licensed under CC BY 4.0.
← All ai models