AuroraAI-Research/Aurora2-400M-A20M
text-generation model by AuroraAI-Research
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
Aurora2-400M-A20M is a decoder-only language model with approximately 400M total parameters and 19M active parameters per token. It uses a top-1 Mixture-of-Experts (MoE) architecture with 32 routed experts and one shared expert per layer. The model was pretrained from scratch on 100B tokens using a single GPU. It is a base model, not an instruction-tuned assistant: there was no supervised instruction-tuning or RLHF stage. Aurora2 uses a relatively narrow attention stack paired with large, sparse feed-forward layers. Each token is routed to one of 32 experts, alongside the always-active shared expert. The router scales each selected expert's output by its routing probability. There is no expert capacity factor or token dropping. Router training includes a Switch-style load-balancing loss (coefficient 0.01) and router z-loss (coefficient 0.001). Aurora2 uses a byte-level BPE tokenizer trained from scratch. During training, documents were packed together, with each document starting with a BOS token. No EOS…
Read the full model card ↗ · Preview checked 2026-11-21T09:46:34.046Z
Inside the original model card — Document outline
- Aurora2-400M-A20M
- Architecture
- Core configuration
- Additional components
- Tokenizer
- Training data
- Staged data mixture
- Training procedure
- Optimizer configuration
- Evaluation
- Quick start
- Inference notes
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the model card
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: apache-2.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
AuroraAI-Research/Aurora2-400M-A20M is a text-generation model repository published by AuroraAI-Research on Hugging Face. The source reports the transformers library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- text-generation
- Library
- transformers
- Recent downloads (30 days)
- 643
- Cumulative likes
- 43
- Hugging Face trending score
- 32
- Reported safetensors parameters
- 399,597,454
- Architecture
- Aurora2ForCausalLM
- License
- apache-2.0
- Access
- Not gated by Hugging Face
- Created
- 2026-11-18T19:08:37.000Z
- Last modified
- 2026-11-18T20:11:10.000Z
Compatibility and lineage
Reported languages: en
Base-model lineage was not included.
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-11-21T07:00:33.109Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.