Atlas

Models

← All models

GPT-NeoX-20B

EleutherAI · 2022-04-07 · 20.6B parameters

GPT-NeoX-20B is EleutherAI's dense 20,554,567,680-parameter autoregressive language model trained on the Pile, with weights released under Apache-2.0 in April 2022. It uses 44 transformer layers, a 2,048-token sequence length, rotary positional embeddings on 25% of the embedding dimensions, and parallel attention and feed-forward blocks. At paper submission, the authors described it as the largest dense autoregressive model with publicly available weights.

Benchmark scores

BenchmarkScore
ARC AI241.1
BBH (Open LLM Leaderboard v2)31.7
Capability78.2
GPQA (Open LLM Leaderboard v2)24.3
GSM8K5.3
IFEval (Open LLM Leaderboard v2)25.9
MATH Level 5 (Open LLM Leaderboard v2)1.4
MMLU33.6
MMLU-Pro (Open LLM Leaderboard v2)11.6
MuSR (Open LLM Leaderboard v2)36.5
OpenBookQA38.8
PIQA76.7
WinoGrande66.1
Loading Atlas data…