add README.md

2f47fbc verified 2 months ago

2.65 kB

---
language: [ar]
license: apache-2.0
library_name: transformers
base_model: oddadmix/Nawah-BERT-6M-v2
datasets: [oddadmix/arabic-prompt-routing]
tags: [arabic, zero-shot-classification, prompt-routing, router, bert, encoder, tiny-model]
---
# Nawah-Router-BERT-6M-v2 — موجّه عربي صفري

Give it a text and **any categories in plain Arabic**; it scores all of them in
one forward pass. No fixed taxonomy. **5,977,985 parameters** against
[`Nawah-Router-v3`](https://huggingface.co/oddadmix/Nawah-Router-v3)'s
52,049,409 — **8.7× smaller**.

## Results — it beats the 52M on three of four

**All three models scored in one session** by the shipped `eval_router_only.py`;
Router-v3 reproduced its published card (0.9305 / 0.6976 / 0.6130 / 0.9008).

| eval | Router-v3 (Llama, 52M) | BERT-6M **v1** | **this model, v2** | random |
|---|---|---|---|---|
| unseen category sets | 0.9308 | 0.9137 | **0.9327** | 0.2137 |
| unseen domains | 0.6975 | 0.6696 | **0.7009** | 0.2521 |
| unseen axes | **0.6127** | 0.6024 | 0.6000 | 0.2358 |
| deliberately adjacent categories | 0.9017 | 0.8924 | **0.9101** | 0.2109 |

A 6M encoder **outperforms the 52M decoder** on unseen category sets (+0.2),
unseen domains (+0.3) and adjacent categories (+0.8), at **1/8.7 the size**.

**It loses on unseen axes** — 0.6000 against 0.6127 — and that is the column the
original card calls its strongest claim: `tools` and `retrieval` appear nowhere
in training. Note also that v2 is *worse* than v1 there (0.6024), the only
metric across all three tasks where more pretraining hurt. Three of the four
margins are under one point, which is within what a single run can tell you.

## Why no pooling change was needed

`RouterModel` pools each category's **token span** via `bmm(cat_pool, hidden)`
rather than a fixed position, so it is architecture-agnostic and a BERT backbone
drops in unchanged. The sibling
[`Nawah-Guard-BERT-6M-v2`](https://huggingface.co/oddadmix/Nawah-Guard-BERT-6M-v2)
needed a mean-pooling patch; this did not.

## Usage

```python
from transformers import AutoTokenizer
from routing_model import RouterModel, route      # ships in this repo
M = "oddadmix/Nawah-Router-BERT-6M-v2"
tok = AutoTokenizer.from_pretrained(M)
model = RouterModel.from_pretrained(M)
route(model, tok, "كم صار سعر صرف الدولار اليوم؟",
      ["بحث في الويب", "حاسبة", "تقويم ومواعيد", "لا يحتاج أداة"])
```

Trained on `oddadmix/arabic-prompt-routing` (207,097 rows, 12 axes) with the
dataset's own `train_router_head.py` at its defaults — decoder-tuned.

© KAND CA 2026 — PROJECT NAWAH

	---
	language: [ar]
	license: apache-2.0
	library_name: transformers
	base_model: oddadmix/Nawah-BERT-6M-v2
	datasets: [oddadmix/arabic-prompt-routing]
	tags: [arabic, zero-shot-classification, prompt-routing, router, bert, encoder, tiny-model]
	---

	# Nawah-Router-BERT-6M-v2 — موجّه عربي صفري

	Give it a text and any categories in plain Arabic; it scores all of them in
	one forward pass. No fixed taxonomy. 5,977,985 parameters against
	[`Nawah-Router-v3`](https://huggingface.co/oddadmix/Nawah-Router-v3)'s
	52,049,409 — 8.7× smaller.

	## Results — it beats the 52M on three of four

	All three models scored in one session by the shipped `eval_router_only.py`;
	Router-v3 reproduced its published card (0.9305 / 0.6976 / 0.6130 / 0.9008).

	\| eval \| Router-v3 (Llama, 52M) \| BERT-6M v1 \| this model, v2 \| random \|
	\|---\|---\|---\|---\|---\|
	\| unseen category sets \| 0.9308 \| 0.9137 \| 0.9327 \| 0.2137 \|
	\| unseen domains \| 0.6975 \| 0.6696 \| 0.7009 \| 0.2521 \|
	\| unseen axes \| 0.6127 \| 0.6024 \| 0.6000 \| 0.2358 \|
	\| deliberately adjacent categories \| 0.9017 \| 0.8924 \| 0.9101 \| 0.2109 \|

	A 6M encoder outperforms the 52M decoder on unseen category sets (+0.2),
	unseen domains (+0.3) and adjacent categories (+0.8), at 1/8.7 the size.

	It loses on unseen axes — 0.6000 against 0.6127 — and that is the column the
	original card calls its strongest claim: `tools` and `retrieval` appear nowhere
	in training. Note also that v2 is worse than v1 there (0.6024), the only
	metric across all three tasks where more pretraining hurt. Three of the four
	margins are under one point, which is within what a single run can tell you.

	## Why no pooling change was needed

	`RouterModel` pools each category's token span via `bmm(cat_pool, hidden)`
	rather than a fixed position, so it is architecture-agnostic and a BERT backbone
	drops in unchanged. The sibling
	[`Nawah-Guard-BERT-6M-v2`](https://huggingface.co/oddadmix/Nawah-Guard-BERT-6M-v2)
	needed a mean-pooling patch; this did not.

	## Usage

	```python
	from transformers import AutoTokenizer
	from routing_model import RouterModel, route # ships in this repo

	M = "oddadmix/Nawah-Router-BERT-6M-v2"
	tok = AutoTokenizer.from_pretrained(M)
	model = RouterModel.from_pretrained(M)

	route(model, tok, "كم صار سعر صرف الدولار اليوم؟",
	["بحث في الويب", "حاسبة", "تقويم ومواعيد", "لا يحتاج أداة"])
	```

	Trained on `oddadmix/arabic-prompt-routing` (207,097 rows, 12 axes) with the
	dataset's own `train_router_head.py` at its defaults — decoder-tuned.

	© KAND CA 2026 — PROJECT NAWAH