fjolsvin/Qwythos-9B-v2-tiiny
image-text-to-text model by fjolsvin
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.
Imported from this repo onto a Tiiny Pocket (TiinyOS 0.1.39) and tested on 2026-11-17: Full report: tiiny-verification.md (raw data in tiiny-verification.json). Empero AI The next iteration of Qwythos: all the reasoning of Qwythos-9B, with the looping behavior fixed. v2 keeps the deep chain-of-thought, the uncensored research posture, and the 1M-token context of its predecessor, and cleans up the rough edges that showed up in real use. The fix uses FTPO (Final-Token Preference Optimization): we identify the exact token that starts a repetition loop and gently train the model to prefer coherent alternatives at that one position, leaving the rest of the distribution — and therefore the model's knowledge and reasoning — untouched. Measured with our internal harness (generative chain-of-thought, greedy/pass@1 unless noted; MMLU/ARC/GSM8K n=500, GPQA-diamond n=198, HumanEval n=164). Judge for the quality metric: an independent LLM grader. Capability is preserved across the board vs. the base Qwythos (differences are within…
Read the full model card ↗ · Preview checked 2026-11-17T07:35:17.833Z
Inside the original model card — Document outline
- Tiiny Pocket verification
- Qwythos-9B-v2 — the new and improved Qwythos
- What got fixed & improved (vs. the base Qwythos)
- Evaluations
- Sample generations
- Recommended sampling
- Long context
- Model details
- Training procedure
- Usage
- Limitations
- Acknowledgements
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
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
fjolsvin/Qwythos-9B-v2-tiiny is a image-text-to-text model repository published by fjolsvin 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
- 9,653,104,368
- Architecture
- Qwen3_5ForConditionalGeneration
- License
- apache-2.0
- Access
- Not gated by Hugging Face
- Created
- 2026-11-17T06:08:37.000Z
- Last modified
- 2026-11-17T06:26:03.000Z
Compatibility and lineage
Reported languages: en
Reported base models: Qwen/Qwen3.5-9B
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 2026-11-17T07:01:06.441Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.