Instructions to use Janeodum/tsaro-e4b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Janeodum/tsaro-e4b with Transformers:

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

pipe = pipeline("text-generation", model="Janeodum/tsaro-e4b")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("Janeodum/tsaro-e4b")
model = AutoModelForMultimodalLM.from_pretrained("Janeodum/tsaro-e4b")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Janeodum/tsaro-e4b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Janeodum/tsaro-e4b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Janeodum/tsaro-e4b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Janeodum/tsaro-e4b

SGLang

How to use Janeodum/tsaro-e4b 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 "Janeodum/tsaro-e4b" \
    --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": "Janeodum/tsaro-e4b",
		"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 "Janeodum/tsaro-e4b" \
        --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": "Janeodum/tsaro-e4b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Janeodum/tsaro-e4b with Docker Model Runner:
```
docker model run hf.co/Janeodum/tsaro-e4b
```

tsaro-e4b / README.md

Janeodum

Upload README.md with huggingface_hub

7b22d48 verified about 2 months ago

preview code

Raw

History Blame Contribute Delete

1.55 kB

	---
	license: gemma
	base_model: google/gemma-4-E4B-it
	base_model_relation: finetune
	library_name: transformers
	tags:
	- gemma-4
	- tsaro
	- threat-extraction
	language:
	- ha
	- en
	pipeline_tag: text-generation
	---

	# Tsaro Gemma 4 E4B

	Fine-tuned Gemma 4 E4B threat extraction model for Tsaro, a shared safety
	system for Northern Nigeria.

	## What this model does

	Given an unstructured report in Hausa, Pidgin, or English, this model returns
	a structured threat signal — threat type, location, perpetrator and vehicle
	counts, direction of movement, time references, and a confidence score — and
	judges whether the message is a genuine security report at all.

	## Model details

	- Base model: [`google/gemma-4-E4B-it`](https://huggingface.co/google/gemma-4-E4B-it)
	- Fine-tuning: LoRA adapter trained on Tsaro threat-report data, then merged
	into the base weights
	- Role in Tsaro: E4B is the primary on-device extraction model — the default
	on any reasonably modern Android device. The Tsaro app loads the largest model
	the hardware can run, falling back from E4B to E2B to a hosted endpoint.

	## Training data

	Fine-tuned on 35,512 examples spanning Hausa, Pidgin, and English: 2,500
	synthetic threat reports plus 33,262 examples derived from the ACLED Nigeria
	conflict archive, each paired with Hausa and Pidgin translations.

	## Intended use and limitations

	Built for community safety reporting in a specific regional context. Not a
	general-purpose model. Outputs are extraction assistance, not verified
	intelligence.