Instructions to use org2ai/Wald-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use org2ai/Wald-4B with Transformers:

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

pipe = pipeline("text-generation", model="org2ai/Wald-4B")
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)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("org2ai/Wald-4B")
model = AutoModelForMultimodalLM.from_pretrained("org2ai/Wald-4B", device_map="auto")
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=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use org2ai/Wald-4B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "org2ai/Wald-4B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "org2ai/Wald-4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/org2ai/Wald-4B

SGLang

How to use org2ai/Wald-4B 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 "org2ai/Wald-4B" \
    --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": "org2ai/Wald-4B",
		"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 "org2ai/Wald-4B" \
        --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": "org2ai/Wald-4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use org2ai/Wald-4B with Docker Model Runner:
```
docker model run hf.co/org2ai/Wald-4B
```

Wald-4B / docs /readmes

Commit History

Oct 8 7 days ago

15:10
Wald-Q4B v2 (04701-c22 + Qwen3.5-4B vision tower): main = v2; v1.x at tags v1.2 / v1.2-main / v1.1 / v1.0

org2ai

ef7481d
07:54
Card: point v1.2 file links at the cleaned v1.2-release branch⁠

Harry19081

Verified signature
a5d6e74
07:44
Card: describe teacher models as large frontier models⁠

Harry19081

Verified signature
9d10516

Oct 1 14 days ago

06:58
Card: GGUF / llama.cpp / Ollama section (EN + ZH), tags; wald-serve 0.1.1 (llama.cpp backend, vLLM path unchanged); MANIFEST with the GGUF files

Harry19081

Verified signature
9662694
06:01
main = Wald-Q4B v1.2 (02600-f19, robustness release): weights from v1.2-release, v1.2 serving.json (effort none) and runbook; card: v1.2 on main, v1.1 at tag v1.1

Harry19081

Verified signature
981b91b
04:01
Card update: repository moved to org2ai (2026-10-01); paths and links point to org2ai

Harry19081

Verified signature
4607c2b

Sep 30 15 days ago

17:30
Model card: announce Wald-Q4B v1.2 (robustness release, revision v1.2); weights on main unchanged (v1.1)

Harry19081

Verified signature
0b72e5a

Sep 29 16 days ago

09:13
Model card: clearer summary, FAQ, related projects, JevBench result, model-index; add API reference, CITATION.cff, llms.txt

Harry19081

Verified signature
1f96041
04:37
Refresh bilingual v1.1 model card: thinking effort, serving and Jev discovery

Harry19081

Verified signature
b1b4c4c
04:12
Release Wald-Q4B22D0-f7: full DI0.2.1 54.59 and clean calibration⁠

Harry19081

Verified signature
503dfd6

Sep 27 18 days ago

09:51
Wald-4B v1.0

Harry19081

78ebf43

Commit History

Oct 8 7 days ago

Wald-Q4B v2 (04701-c22 + Qwen3.5-4B vision tower): main = v2; v1.x at tags v1.2 / v1.2-main / v1.1 / v1.0

Card: point v1.2 file links at the cleaned v1.2-release branch⁠

Card: describe teacher models as large frontier models⁠

Oct 1 14 days ago

Card: GGUF / llama.cpp / Ollama section (EN + ZH), tags; wald-serve 0.1.1 (llama.cpp backend, vLLM path unchanged); MANIFEST with the GGUF files

main = Wald-Q4B v1.2 (02600-f19, robustness release): weights from v1.2-release, v1.2 serving.json (effort none) and runbook; card: v1.2 on main, v1.1 at tag v1.1

Card update: repository moved to org2ai (2026-10-01); paths and links point to org2ai

Sep 30 15 days ago

Model card: announce Wald-Q4B v1.2 (robustness release, revision v1.2); weights on main unchanged (v1.1)

Sep 29 16 days ago

Model card: clearer summary, FAQ, related projects, JevBench result, model-index; add API reference, CITATION.cff, llms.txt

Refresh bilingual v1.1 model card: thinking effort, serving and Jev discovery

Release Wald-Q4B22D0-f7: full DI0.2.1 54.59 and clean calibration⁠

Sep 27 18 days ago

Wald-4B v1.0