Instructions to use oddadmix/Nawah-Math-Reasoning with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use oddadmix/Nawah-Math-Reasoning with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="oddadmix/Nawah-Math-Reasoning")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("oddadmix/Nawah-Math-Reasoning")
model = AutoModelForCausalLM.from_pretrained("oddadmix/Nawah-Math-Reasoning", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use oddadmix/Nawah-Math-Reasoning with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "oddadmix/Nawah-Math-Reasoning"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "oddadmix/Nawah-Math-Reasoning",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/oddadmix/Nawah-Math-Reasoning

SGLang

How to use oddadmix/Nawah-Math-Reasoning with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "oddadmix/Nawah-Math-Reasoning" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "oddadmix/Nawah-Math-Reasoning",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "oddadmix/Nawah-Math-Reasoning" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "oddadmix/Nawah-Math-Reasoning",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use oddadmix/Nawah-Math-Reasoning with Docker Model Runner:
```
docker model run hf.co/oddadmix/Nawah-Math-Reasoning
```

Nawah-Math-Reasoning / code /space /README.md

oddadmix

training code: data generation, SFT, eval, GRPO

867d0f3 verified 4 days ago

preview code

Raw

History Blame Contribute Delete

3.56 kB

metadata

title: Nawah Math Reasoning
emoji: 🧠
colorFrom: indigo
colorTo: purple
sdk: gradio
sdk_version: 6.26.0
python_version: '3.12'
app_file: app.py
pinned: false
models:
  - oddadmix/Nawah-Math-Reasoning
datasets:
  - oddadmix/arabic-math-reasoning-synth
  - oddadmix/gsm8k-reasoning-ar
short_description: نموذج استدلال رياضي عربي (52M) يفكّر خطوة بخطوة قبل الإجابة

Nawah-Math-Reasoning — Demo

A 51.8M-parameter Arabic math reasoning model. It writes its derivation inside <think>…</think> and then gives the final answer; the demo splits the two live as it streams — the reasoning trace in one panel, the answer in the other.

Fine-tuned from oddadmix/50M-2048-Emhotob, a Llama-architecture base pre-trained from scratch on ~20B Arabic tokens (12 layers, hidden 512, 2048 context).

بالعربية: نموذج عربي صغير (~52 مليون معامل) يكتب خطوات تفكيره داخل وسم <think> ثم يعطي الإجابة النهائية. الديمو بيفصل الاتنين وانت بتتفرج على النموذج وهو بيكتب.

Everything is open — Apache 2.0


🧠 Model	`oddadmix/Nawah-Math-Reasoning`
🛠️ Training code	`code/` — data generation, translation, SFT, eval, GRPO
📚 Synthetic corpus	`oddadmix/arabic-math-reasoning-synth` — 120,462 arithmetically verified rows
📚 Translated corpus	`oddadmix/gsm8k-reasoning-ar` — 142,969 rows

Results

Number agreement, greedy decoding, on held-out splits. Every version of the model was scored on identical rows, so the numbers are comparable across the whole development ladder.

eval set	n	score
GSM8K-ar	600	79.0%
Arabic_Reasoning	400	73.0%
synthetic math	1000	40.4%
synthetic relational	400	52.2%

The last row is what this release adds: problems where the difficulty is the relation between quantities (ضعف, نصف, أكثر بـ…) rather than the arithmetic. The previous version scored 34.0% there — the relation appeared in barely 1.3% of the training corpus, so 20,139 rows were generated specifically to fill the gap.

Limitations

A 52M proof of concept. It reliably produces the shape of Arabic step-by-step reasoning, but arithmetic errors are the dominant failure mode — the derivation is usually structurally right, one computation is wrong, and the model then stays faithful to its own bad number. The 40.4% and 52.2% above are the honest ceiling on multi-step problems. Single-turn only; open-ended and non-mathematical questions are out of distribution.

نموذج تجريبي: بيعرف يمشي خطوة خطوة بالعربي، بس بيغلط في الحساب كتير.

Runs on ZeroGPU. The model is small enough for CPU too — switch the Space to cpu-basic and it still works, just slower.

Configuration

Variable	Purpose
`MODEL_ID`	Model repo to load (default `oddadmix/Nawah-Math-Reasoning`)
`MODEL_HF_TOKEN`	Only needed if `MODEL_ID` points at a private repo. (`HF_TOKEN` is reserved by Spaces and does not reach the container.)