Model Detail
gpt2
—gpt2 is a large language model with 69M parameters released by openai-community. The model is registered under the text-generation pipeline tag on Hugging Face, distributed under the permissive mit license.
Open-LLM-Leaderboard scoring places it at MMLU-Pro 2, GPQA 1, IFEval 18, BBH 3, giving a sense of how it handles instruction following, reasoning, and graduate-level QA in absolute terms.
gpt2 ships as a GPT2LMHeadModel / 🟢 pretrained architecture with 69M parameters. The mit license is permissive, allowing commercial deployment and derivative work without per-seat fees, though attribution requirements still apply.
Downloads of gpt2 have moved -3.8% over the trailing seven days. That is a slight downtrend, consistent with normal cooling as newer models compete for the same workloads. These numbers are signal, not guarantee — week-over-week download counts on Hugging Face also reflect mirror traffic, CI scrapes, and one-off benchmarking runs.
gpt2 is best fit for general-purpose chat and instruction-following workloads. Treat this as a starting matrix rather than a benchmark verdict — the right deployment usually depends on the specific evaluation suite that mirrors your workload.
Benchmarking EngGPT2-16B-A3B against Comparable Italian and International Open-source LLMs
arXiv:2605.07731v2 Announce Type: replace-cross Abstract: This report benchmarks the performance of ENGINEERING Ingegneria Informatica S.p.A.'s EngGPT2MoE-16B-A3B LLM, a 16B parameter Mixture of Experts (MoE) model with 3B active parameters. Performance is investigated across a wide variety of repre
EngGPT2: Sovereign, Efficient and Open Intelligence
arXiv:2603.16430v3 Announce Type: replace-cross Abstract: EngGPT2-16B-A3B is the latest iteration of Engineering Group's Italian LLM and it's built to be a Sovereign, Efficient and Open model. EngGPT2 is trained on 2.5 trillion tokens - less than Qwen3's 36T or Llama3's 15T - and delivers performanc
