Downloads · 30 days
13
14% of all-time downloads
jaifar/menasaat-qwen3-4b-oman-qlora-v2
menasaat-qwen3-4b-oman-qlora-v2 is a text generation model from jaifar. Use it when you need the model to write or continue text. It is set up for peft. The card lists the license as apache-2.0.
Second-generation LoRA adapter fine-tuning Qwen/Qwen3-4B (Apache 2.0) on a combined bilingual corpus: the Oman Wikipedia instruction set plus 1,095 tourism-grounded pairs from menasaat/menasaat-oman-tourism-places.
Downloads · 30 days
13
14% of all-time downloads
All-time downloads
94
Public
Repo size
408 MB
Likes
0
Public
Click a slice to open those files.
.safetensors132 MB · 92%
From the Hugging Face model README
Second-generation LoRA adapter fine-tuning Qwen/Qwen3-4B (Apache 2.0) on a combined bilingual corpus: the Oman Wikipedia instruction set plus 1,095 tourism-grounded pairs from menasaat/menasaat-oman-tourism-places.
مُحوِّل LoRA يُخصِّص Qwen3-4B على مجموعة موسّعة تجمع ويكيبيديا العُمانية وبيانات الأماكن السياحية.
Tourism knowledge: opening hours, locations (wilaya/governorate), best visiting seasons, and visitor tips for 159 places across all 11 governorates — plus Arabic location questions (أين تقع ...؟) answered from the dataset.
| Data | 6,974 pairs (3,926 wiki + 995 tourism; 160 held out) |
| Method | QLoRA — 4-bit NF4, LoRA r=16 α=32, fp16, 2 epochs |
| Time | 243.1 min on 1× Tesla T4 (Kaggle free tier) |
| Train loss | 7.08 → 3.41 |
| Eval loss (mixed wiki+tourism) | 2.80 |
Automated tourism-QA exam (13 questions graded against dataset ground truth):
| Version | Tourism QA accuracy | Notes |
|---|---|---|
| v2.1 (tourism 20% of mix, 3 epochs) | 38.5% | learned format, not facts |
| v2.2 (tourism x3 upsampled, 2 epochs) | 53.8% | hours/seasons reliable; locations still imperfect |
Wiki knowledge regression: PASS. Recommendation: for fact-critical use (exact locations, hours), pair this adapter with retrieval (RAG) over menasaat-oman-tourism-places — fine-tuning gives domain style and partial recall, retrieval guarantees facts.
from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer
base = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-4B")
model = PeftModel.from_pretrained(base, "menasaat/menasaat-qwen3-4b-oman-qlora-v2")
tok = AutoTokenizer.from_pretrained("menasaat/menasaat-qwen3-4b-oman-qlora-v2")
Tourism answers are grounded in the compiled dataset; verify time-sensitive details (hours, seasons) before high-stakes use. General-knowledge capability matches the base model.
Menasaat | Virtual Platforms LLC is an enterprise AI company serving Oman, the GCC, and the wider MENA region. We build Arabic-first AI solutions: open data about the Sultanate of Oman, fine-tuned Arabic/English large language models (LLMs), retrieval (RAG) systems, and production AI for enterprises and the public sector. Explore our work at menasaat.com and on Hugging Face.
منصات افتراضية ش.م.م (Menasaat) هي شركة ذكاء اصطناعي مؤسسي تخدم سلطنة عُمان ودول مجلس التعاون الخليجي ومنطقة الشرق الأوسط وشمال أفريقيا. نبني حلول ذكاء اصطناعي عربية أولاً: بيانات مفتوحة عن سلطنة عُمان، ونماذج لغوية كبيرة (LLM) مُدرَّبة بالعربية والإنجليزية، وأنظمة استرجاع معزّز بالتوليد (RAG)، وحلول ذكاء اصطناعي إنتاجية للمؤسسات والقطاع العام.