Instructions to use ssh2025/brunei-malay-normalizer-v4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ssh2025/brunei-malay-normalizer-v4 with Transformers:

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

pipe = pipeline("text-generation", model="ssh2025/brunei-malay-normalizer-v4")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("ssh2025/brunei-malay-normalizer-v4", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ssh2025/brunei-malay-normalizer-v4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ssh2025/brunei-malay-normalizer-v4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ssh2025/brunei-malay-normalizer-v4",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ssh2025/brunei-malay-normalizer-v4

SGLang

How to use ssh2025/brunei-malay-normalizer-v4 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 "ssh2025/brunei-malay-normalizer-v4" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ssh2025/brunei-malay-normalizer-v4",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "ssh2025/brunei-malay-normalizer-v4" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ssh2025/brunei-malay-normalizer-v4",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ssh2025/brunei-malay-normalizer-v4 with Docker Model Runner:
```
docker model run hf.co/ssh2025/brunei-malay-normalizer-v4
```

Brunei Malay Normalizer V4

V4 is the frozen trial-qwen3-4b-structure-z-20260909 candidate, approved by the project owner on 2026-09-10 for release and manual testing with documented regression limitations. It normalizes Brunei Malay into Standard Malay. It does not answer questions or provide medical advice.

Use the complete runtime, not a bare Transformers pipeline: source-conditioned knowledge, clause/layout handling and literal/surface protection are part of the tested system. Model weights are under model/. Run serve.py as described in DEPLOYMENT.md. Weights are merged, non-quantized; serving uses FP16, greedy decoding and the frozen layout policy. The model derives from Qwen3-4B-Instruct-2507 at revision cdbee75f17c01a7cc42f958dc650907174af0554.

Actual regression evidence

Suite	Frozen accepted-output agreement	Required dimensions
G	1234/1248	All >=90%
H-r2	2460/2473	All >=90%
I (consumed regression)	1314/1320	All >=90%
W long text	177/192	Changed 134/149 = 89.93%; copy 43/43
Historical regression	9208/9228	All >=90%
Surface/typography	743/768	All >=90%
Clause boundaries	274/274	All >=90%

All 15,503 original-message predictions were recomputed and their recorded model/runtime/reference fingerprints verified; zero per-message runtime errors. See evaluation-summary.json for every dimension and evidence hashes. These are correlated authored scenarios, typography variants and recombinations, not 15,503 independent users. I is no longer independent acceptance evidence.

The W disagreements comprise 13 rejected cases (asking-event deletion, invented ownership, Nada changed to Tiada, or missing kana tanya normalization) and two unresolved pasal/tentang Standard Malay register cases. Unresolved cases remain unaccepted in the conservative score. No reference was changed to pass the gate. Fresh X-r2/AA/AB and native population acceptance have not been completed. Owner release approval is an explicit exception, not an all-dimensions-pass claim.

Preserve source meaning, voice, participants, negation, time and quantities; already-Standard Malay should remain unchanged. Correct ordinary English translation within routed mixed Malay is allowed by the evaluation policy, though the frozen training prompt still instructs copying those spans. Wholly non-Malay language routing belongs upstream. Known errors remain; review outputs before consequential use.

Package and provenance

release-manifest.json records SHA-256 and size for every release file. report.json is an allowlisted training/runtime summary; its original report hash is retained. Z's last 1,024-row calibration epoch is not the whole training corpus. Its parent-trial/report hashes preserve that distinction. Knowledge cards and runtime code are required reconstruction inputs. Private training/test payloads, patient records, product workbooks and source-paper originals are not included.

The base-model Apache 2.0 notice is retained in BASE_MODEL_LICENSE.txt.

Downloads last month: -; Downloads are not tracked for this model. How to track

Model tree for ssh2025/brunei-malay-normalizer-v4

Base model

Qwen/Qwen3-4B-Instruct-2507

Finetuned

(2129)

this model