aamohame/qwen25-7b-fr-journalism-v07
text-generation model by aamohame
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.
This repository contains a LoRA adapter for Qwen/Qwen2.5-7B-Instruct. It is not a standalone model. It was fine-tuned for six French journalism task families. 2500 selected examples from pinned source datasets; subtype counts: {'qaanswerable': 540, 'summary': 250, 'editingalpaca': 40, 'newsroom': 400, 'qarefusal': 180, 'editingsynthetic': 360, 'headline': 250, 'editorialloaded': 75, 'factsupported': 90, 'editorialclean': 75, 'editorialneutralize': 150, 'factinsufficient': 45, 'factrefuted': 45}. 2284 were used for training, and source groups were held out. Source construction methods and revisions are in experimentmetadata.json. No benchmark tasks or French X-Fact zero-shot rows were used for training. Loss was measured on 216 held-out examples. ROUGE-L uses up to five generated examples per task, so…
Read the full model card ↗ · Preview checked 2026-10-27T23:40:47.598Z
Inside the original model card — Document outline
- Qwen2.5 7B French Journalism v07
- Identity and provenance
- Training configuration
- Training data
- Held-out evaluation
- Limitations
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. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
aamohame/qwen25-7b-fr-journalism-v07 is a text-generation model repository published by aamohame 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
- Not reported — check the model card
- Access
- Not gated by Hugging Face
- Created
- 2026-10-19T05:59:40.000Z
- Last modified
- 2026-10-19T05:59:44.000Z
Compatibility and lineage
Language coverage was not reported.
Reported base models: Qwen/Qwen2.5-7B-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 2026-10-19T06:43:13.200Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.