Instructions to use purbeshmitra/semantic-soft-bootstrapping with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use purbeshmitra/semantic-soft-bootstrapping with Transformers:

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

pipe = pipeline("text-generation", model="purbeshmitra/semantic-soft-bootstrapping")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("purbeshmitra/semantic-soft-bootstrapping", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use purbeshmitra/semantic-soft-bootstrapping with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/purbeshmitra/semantic-soft-bootstrapping

SGLang

How to use purbeshmitra/semantic-soft-bootstrapping 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 "purbeshmitra/semantic-soft-bootstrapping" \
    --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": "purbeshmitra/semantic-soft-bootstrapping",
		"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 "purbeshmitra/semantic-soft-bootstrapping" \
        --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": "purbeshmitra/semantic-soft-bootstrapping",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Desktop
Docker Model Runner
How to use purbeshmitra/semantic-soft-bootstrapping with Docker Model Runner:
```
docker model run hf.co/purbeshmitra/semantic-soft-bootstrapping
```

purbeshmitra commited on Dec 5, 2025

Commit

3868889

verified ·

1 Parent(s): bd69ba2

Update README.md

Browse files

Files changed (1) hide show

README.md +12 -1

README.md CHANGED Viewed

@@ -20,4 +20,15 @@ metrics:
 # Semantic Soft Bootstrapping (SSB)
-🔗 Paper link: [Arxiv preprint](https://arxiv.org/abs/2512.05105)

 # Semantic Soft Bootstrapping (SSB)
+🔗 Paper link: [Arxiv preprint](https://arxiv.org/abs/2512.05105)
+## Citation
+If you find our work useful, consider citing it as:
+```bibtex
+@article{mitra2025semantic,
+  title={Semantic Soft Bootstrapping: Long Context Reasoning in LLMs without Reinforcement Learning},
+  author={Mitra, Purbesh and Ulukus, Sennur},
+  journal={arXiv preprint arXiv:2512.05105},
+  year={2025}
+}
+```