joey00072/ohara-d28-a1b-s5a
AI model by joey00072
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.
Stage-1 pretraining checkpoint (4k context) of the ohara hybrid causal encoder-decoder: d28 finalv2 (SWA + KV-bridged global + token-sparse attention, mHC residual, n-gram memory, 256-expert MoE top-8 + shared expert), 0.98B active backbone matrix parameters (1.25B incl. the LM head) / 23.85B total parameters, Qwen3 tokenizer.…
Read the full model card ↗ · Preview checked 2026-11-08T08:15:25.931Z
Inside the original model card — Document outline
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Documentation belongs to its respective authors. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
joey00072/ohara-d28-a1b-s5a is a task-unspecified model repository published by joey00072 on Hugging Face. The source reports the ohara library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- Not reported
- Library
- ohara
- Recent downloads (30 days)
- 0
- Cumulative likes
- 0
- Hugging Face trending score
- 0
- Reported safetensors parameters
- 23,846,942,486
- Architecture
- HybridCED
- License
- Not reported — check the model card
- Access
- Not gated by Hugging Face
- Created
- 2026-11-08T06:38:40.000Z
- Last modified
- 2026-11-08T06:43:14.000Z
Compatibility and lineage
Language coverage was not reported.
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 2026-11-08T06:55:28.597Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.