gemma-4-e2b-yemeni-arabic-assistant-merged is a full merged BF16 safetensors model based on Gemma 4 E2B Instruct, with the Yemeni Arabic LoRA adapter merged into the base model for responses in broad Yemeni Arabic.
The goal of this adapter is not to create a new general-purpose model from scratch. It is a dialect adaptation experiment: it pushes a capable Arabic/English instruction model toward Yemeni-style wording, shorter local responses, Yemeni dialect rewriting, and translation into Yemeni Arabic while preserving the base model's general instruction-following ability as much as possible.
Yemeni Arabic is underrepresented in public LLM resources. This release is intended to support research and practical experimentation around low-resource Arabic dialect adaptation, especially for Yemeni Arabic assistant responses.
To the best of our knowledge, this is the first publicly released model focused specifically on Yemeni Arabic assistant-style responses.
Model Details
Model name:gemma-4-e2b-yemeni-arabic-assistant-lora
Task type: Text generation / conversational assistant / dialect rewriting
Adapter format: PEFT LoRA
Intended Use
This adapter is intended for:
Yemeni Arabic assistant responses
Yemeni dialect rewriting
Translation or adaptation into Yemeni Arabic
Short localized Arabic assistant replies
Yemeni vocabulary and expression experiments
Research on low-resource Arabic dialect fine-tuning
Evaluation of synthetic and grounded data for dialect adaptation
Example use cases:
text
1User: ترجم للهجة اليمنية: I am tired today and I do not want to go out.
2Assistant: أنا تعبان اليوم وما اشتي أخرج.
text
1User: اكتبها بطريقة يمنية أبسط: لا أريد أن أتكلم عن الموضوع الآن.
2Assistant: ما اشتي أتكلم عن الموضوع ذلحين.
text
1User: رد على: وينك مختفي؟
2Assistant: موجود والله بس اليوم كان فوق رأسي شغل.
Training Data
The adapter was trained on 19,609 cleaned Yemeni Arabic assistant-style samples.
The dataset was built from a mixture of locally collected and generated resources, including:
Yemeni social-media style text collected from public/community sources
Yemeni examples derived from Arabic dialect identification data
Yemeni vocabulary and expression references
Local dictionary-style resources
Grounded teacher-model rewrites and expansions
Filtered task examples for translation, rewriting, Q&A, reasoning, and calculations
The final training file was cleaned with rule-based and LLM-assisted review passes. The cleaning focused on removing or reducing:
Non-target dialect leakage such as Gulf/Egyptian expressions
Overused assistant phrases and service endings
Excessive greetings and formal closings
Repetitive openings such as overuse of "والله" and "شوف"
Long, generic explanations where a direct answer was better
Obvious hallucinated or malformed Yemeni expressions
Known unwanted terms from the current data cleaning pass
The final cleaned dataset used for this run contained:
19,609 rows
Average assistant response length around 150 characters
Maximum assistant response length capped at 360 characters
Training Configuration
The model was trained for 1 epoch using Unsloth.
Parameter
Value
Method
QLoRA
Quantization
4-bit
Epochs
1
Training samples
19,609
Steps
2,436
Context length
1,024
Batch size
2
Learning rate
0.0002
Warmup steps
50
Optimizer
AdamW 8-bit
LoRA rank
32
LoRA alpha
64
LoRA dropout
0
Final training loss
2.4486
Recommended System Prompt
For best results, use a short system prompt that explicitly controls assistant behavior:
text
1أنت مساعد يمني ذكي ومختصر.
2جاوب باللهجة اليمنية الطبيعية.
3لا تضف تحية إلا إذا المستخدم بدأ بتحية.
4لا تختم بسؤال أو عرض مساعدة.
5لا تضف رأيك إلا إذا المستخدم طلب رأيك.
6في الترجمة أو إعادة الصياغة: أعطِ النص فقط بدون شرح.
If the model becomes too chatty, reduce max_new_tokens first. Many assistant-style continuation problems come from allowing the model to generate far past the natural answer length.
Yemeni Arabic is not one dialect. It includes substantial regional variation across Sana'a, Taiz, Aden, Ibb, Hadramout, Tihama, Dhamar, Lahj, Al-Bayda, Marib, and other areas. This adapter targets a broad, practical Yemeni style for assistant use rather than a single city-specific dialect.
The dataset intentionally avoids some expressions that appeared in generated data but were judged unsuitable for the target style, including examples such as non-target vocatives, Gulf-like fillers, and malformed Yemeni phrases.
Limitations
This is an experimental dialect fine-tune.
Known limitations:
The adapter may still produce Modern Standard Arabic on technical, formal, or unfamiliar topics.
The base instruct model may still show polite assistant behavior unless the system prompt and decoding length are controlled.
The model may occasionally overuse common openings such as "والله" or "شوف".
It may hallucinate factual or cultural information if used without retrieval or source grounding.
The training data includes synthetic and teacher-assisted samples, so not every phrase should be treated as corpus-attested Yemeni speech.
It is not a legal, medical, financial, or religious authority.
It does not represent every Yemeni region equally.
It may still require prompt and decoding control for very casual social conversations.
Ethical and Privacy Considerations
The training work used collected and generated Arabic text for dialect adaptation. Public or community-sourced social-media text can contain names, opinions, jokes, and local references. Cleaning passes were applied to reduce low-quality generations and unwanted assistant behavior, but users should not assume the data pipeline guarantees perfect anonymization or factual accuracy.
This model should not be used to impersonate private individuals, generate harassment, or make high-stakes decisions about people.
