Darkrider/nirnaya-turbo-1.0
image-text-to-text model by Darkrider
Older snapshot: check the original source for current information.
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.
Nirnaya (निर्णय) means "decision" in Hindi. The Nirnaya family are decision models: give one a state and a set of questions, and it returns one answer per question with a probability on every option, in a single pass. Nirnaya Turbo 1.0 is the most accurate member of the family. It reads text, images and audio, in English and Indian languages. The figures above come from complete runs of the Decision Index kit. Private board scores are added here once they are published. The model needs the inference code in github.com/NeverInAsh/nirnaya-inference and the Decision Index kit. For the vision suite, use mmclm.diengine:NirnayaVisionEngine with maxsofttokens=560 and maximages=2. For audio, use mmclm.diengine:NirnayaAudioEngine. Install librosa fastapi uvicorn python-multipart, start the HTTP server with python -m mmclm.serve --model --port 8000, and send requests to POST /v1/decisions. The model was fine-tuned on a huge amount of data: about 69% text, 17% images and 14% audio, with…
Read the full model card ↗ · Preview checked 2026-11-10T07:28:23.403Z
Inside the original model card — Document outline
- Nirnaya Turbo 1.0
- How to run it
- Training data
- How we kept test data out of training
- Calibration
- Limits
- Using Nirnaya
- Licence
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
Darkrider/nirnaya-turbo-1.0 is a image-text-to-text model repository published by Darkrider 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
- image-text-to-text
- Library
- transformers
- Recent downloads (30 days)
- 0
- Cumulative likes
- 0
- Hugging Face trending score
- 0
- Reported safetensors parameters
- 26,115,083,856
- Architecture
- Gemma4ForConditionalGeneration
- License
- apache-2.0
- Access
- Not gated by Hugging Face
- Created
- 2026-11-10T06:32:48.000Z
- Last modified
- 2026-11-10T06:34:37.000Z
Compatibility and lineage
Language coverage was not reported.
Reported base models: google/gemma-4-26B-A4B-it
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 2026-11-10T06:56:23.256Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.