Downloads · 30 days
15
9% of all-time downloads
oddadmix/Nawah-50M-Egyptian-18y-Persona
Nawah-50M-Egyptian-18y-Persona is a text generation model from oddadmix. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
Nawah (نواة, "nucleus/seed") is a ~51.8M-parameter Arabic small language model fine-tuned to speak with the voice of an 18-year-old Egyptian persona. It is a proof-of-concept for training capable Arabic models from sc…
Downloads · 30 days
15
9% of all-time downloads
All-time downloads
169
Public
Parameters
51.8M
104 MB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors104 MB · 97%
From the Hugging Face model README
Nawah (نواة, "nucleus/seed") is a ~51.8M-parameter Arabic small language model fine-tuned to speak with the voice of an 18-year-old Egyptian persona. It is a proof-of-concept for training capable Arabic models from scratch at tiny scale — small enough to run on a CPU, yet coherent in Modern Standard Arabic with an Egyptian cultural frame.
oddadmix/50M-2048-Emhotob
— a Llama-architecture model pre-trained from scratch on ~20B Arabic tokens with a
2048-token context window.oddadmix/4.1-mini-18-yearsold-10K
— 9.8K persona-grounded Arabic examples (see Training data).SupraLabs/Supra-50M-Base.
This project is a POC for training Arabic tiny models from scratch.الملخص بالعربية: «نواة» نموذج لغوي عربي صغير (~51.8 مليون معامل) مبني على معمارية Llama ومدرَّب من الصفر، ثم ضُبط ليتحدث بشخصية شاب مصري في الثامنة عشرة من عمره. نموذج تجريبي (Proof of Concept) لإثبات إمكانية تدريب نماذج عربية مفيدة على نطاق صغير جدًا يمكن تشغيلها حتى على المعالج (CPU). التفاصيل الكاملة في الأقسام أدناه.
| Parameters | ~51.8M |
| Architecture | Llama (LlamaForCausalLM) |
| Hidden size | 512 · Layers 12 · Heads 8 (GQA, 4 KV) · head_dim 64 |
| Vocab size | 32002 (32000 base + 2 ChatML control tokens) |
| Context length | 2048 |
| Tied embeddings | yes |
| Chat format | ChatML (`< |
| Precision | bfloat16 |
| License | Apache-2.0 (matches the base architecture) |
Nawah is fine-tuned on oddadmix/4.1-mini-18-yearsold-10K — a
synthetic, persona-grounded Arabic dataset of 9,800 examples covering the life
of an 18-year-old Egyptian (family dynamics, street culture, transport, school/university,
social expectations, and more). Each row carries rich conditioning metadata
(life_stage, domain, persona_seed, socioeconomic_tilt) and multiple output
formats (factual_qa, open_ended_qa, multi_turn), each with an LLM-as-a-judge
quality_evaluation score.
Provenance of the data:
Qwen/Qwen3.5-9B — the
teacher model that generated the persona conversations and answers.البيانات: ضُبط النموذج على مجموعة بيانات اصطناعية مبنية على شخصية مصرية عمرها 18 عامًا (9.8 ألف مثال). البيانات مُقطَّرة من نموذج Qwen 3.5 9B وتم توليدها باستخدام NVIDIA NeMo Data Designer.
The tokenizer uses the TokenizersBackend class, which requires transformers>=5.12.
There is no packaged chat template, so build the ChatML prompt manually:
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
model_id = "oddadmix/Nawah-50M-Egyptian-18y-Persona"
tok = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16)
def chat(user_msg, system="أنت شاب مصري في الثامنة عشرة من عمرك."):
prompt = (
f"<|im_start|>system\n{system}<|im_end|>\n"
f"<|im_start|>user\n{user_msg}<|im_end|>\n"
f"<|im_start|>assistant\n"
)
ids = tok(prompt, return_tensors="pt").to(model.device)
out = model.generate(
**ids, max_new_tokens=256, do_sample=True,
temperature=0.7, top_p=0.9, repetition_penalty=1.2,
eos_token_id=tok.convert_tokens_to_ids("<|im_end|>"),
)
return tok.decode(out[0][ids.input_ids.shape[1]:], skip_special_tokens=True)
print(chat("احكيلي عن يومك في الجامعة."))
You can also try it in the demo Spaces: Nawah-50M-Demo · Nawah-50M-Demo0ts.
Intended use. Research and demonstration of persona-conditioned Arabic generation at tiny scale; lightweight, CPU-friendly Arabic text generation; a baseline for from-scratch Arabic SLM experiments.
Limitations. At ~50M parameters this is a proof of concept, not a
production assistant. Expect limited world knowledge, weak long-form reasoning, and
occasional repetition or factual errors — use sampling with a repetition_penalty.
The persona and its cultural framing come from synthetic data, so outputs reflect
the teacher model's and the persona seed's assumptions rather than any real individual.
Do not rely on it for factual, medical, legal, or financial advice.
SupraLabs/Supra-50M-Base (Apache-2.0).oddadmix/50M-2048-Emhotob — from-scratch, ~20B Arabic tokens, 2048 ctx.oddadmix/4.1-mini-18-yearsold-10K — distilled from Qwen/Qwen3.5-9B, generated with NVIDIA NeMo Data Designer.