Instructions to use aviralku/openclaw-phase1-notes-100m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use aviralku/openclaw-phase1-notes-100m with Transformers:

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

pipe = pipeline("text-generation", model="aviralku/openclaw-phase1-notes-100m")
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("aviralku/openclaw-phase1-notes-100m")
model = AutoModelForMultimodalLM.from_pretrained("aviralku/openclaw-phase1-notes-100m", 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 aviralku/openclaw-phase1-notes-100m with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "aviralku/openclaw-phase1-notes-100m"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "aviralku/openclaw-phase1-notes-100m",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/aviralku/openclaw-phase1-notes-100m

SGLang

How to use aviralku/openclaw-phase1-notes-100m 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 "aviralku/openclaw-phase1-notes-100m" \
    --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": "aviralku/openclaw-phase1-notes-100m",
		"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 "aviralku/openclaw-phase1-notes-100m" \
        --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": "aviralku/openclaw-phase1-notes-100m",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use aviralku/openclaw-phase1-notes-100m with Docker Model Runner:
```
docker model run hf.co/aviralku/openclaw-phase1-notes-100m
```

OpenClaw Phase-1 note TTT — 100M tokens

Private research checkpoint derived from the local Qwen3.8-27B base model by full-parameter next-token training on the balanced OpenClaw recursive-note corpus.

Phase: note-NTP only (Phase 1)
Note-token budget: approximately 100M
Checkpoint: epoch 1, step 3125
Policy KL coefficient: 0.01
Weight dtype: bfloat16
Export format: Hugging Face Transformers, six safetensors shards

export_manifest.json records the exact source checkpoint and export metadata.

Downloads last month: 72

Safetensors

Model size

27B params

Tensor type

BF16