dhrxvie/dugout-writer-qwen2.5-1.5b
text-generation model by dhrxvie
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.
A LoRA fine-tune of Qwen2.5-1.5B-Instruct that writes the briefing notes of dugout, an open-source AI sporting director. It turns fact cards into short prose and never writes a number: values appear only as fact codes ([F3]) that dugout's code replaces with audited, sourced values. Every note must pass dugout's publish gate: no stray numbers, each number bound to its subject and metric, and an NLI Fact-Check of every sentence. 12 clubs never seen in training (bayern-munchen, chelsea, elche, elversberg, espanyol, heerenveen, internazionale, manchester-city, monza, olympique-lyonnais, rennes, utrecht), the dossier's five written sections each. Accepted = passed every gate check (with production's one retry); first try = without it; stray numbers = drafts that wrote a digit or number word (rejected by the auditor). Local models ran on a laptop CPU through Ollama (q4KM, 8k context); Groq's time excludes free-tier rate-limit waits. Why can the student beat its teacher on this…
Read the full model card ↗ · Preview checked 2026-10-29T04:40:48.454Z
Inside the original model card — Document outline
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
dhrxvie/dugout-writer-qwen2.5-1.5b is a text-generation model repository published by dhrxvie on Hugging Face. The source reports the peft 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
- peft
- Recent downloads (30 days)
- 0
- Cumulative likes
- 0
- Hugging Face trending score
- 0
- Reported safetensors parameters
- Not reported
- Architecture
- Not reported
- License
- apache-2.0
- Access
- Not gated by Hugging Face
- Created
- 2026-10-20T06:21:10.000Z
- Last modified
- 2026-10-20T06:23:50.000Z
Compatibility and lineage
Reported languages: en
Reported base models: Qwen/Qwen2.5-1.5B-Instruct
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 2026-10-20T06:43:37.702Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.