---
library_name: transformers
tags:
- text-generation
- maths-reasoning
- math-reasoning
- slm
- reasoning
license: other
license_name: decompute-non-commercial-research-license-v1.0
license_link: https://huggingface.co/decompute/Nebula-S-SVMS2-3B-Internal/blob/main/LICENSE
extra_gated_heading: "Request access to Nebula-S-SVMS2-3B"
extra_gated_button_content: "Acknowledge license and request access"
extra_gated_prompt: "By requesting access, you agree to the Decompute Non-Commercial Research License v1.0. The model may be used only for non-commercial research and evaluation. Commercial use, revenue-generating use, redistribution, sublicensing, hosting, paid API use, SaaS use, production use, customer-facing deployment, fine-tuned redistribution, quantized redistribution, derivative model distribution, and use to train or improve commercial models are prohibited."
extra_gated_fields:
  Full name: text
  Affiliation: text
  Intended use: text
  Commercial entity?: text
  Country: country
---

# Nebula-S-3B

Nebula-S-3B is an internal reasoning model package with custom runtime components.

This package intentionally does not include upstream lineage, source training records, or private provenance. Those records are maintained separately in restricted internal release files.

## Contents

- `core/`: model weights, tokenizer, and generation configuration
- `runtime_weights.safetensors`: runtime weight artifact
- `modeling_nebula.py`: local runtime loader
- `nebula_runtime.py`: import-friendly loader alias
- `release_metadata.json`: neutral package metadata
- `release_manifest.internal.json`: file checksums for this release

## Install

```bash
python3 -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt
```

## Smoke test

Run this from inside the extracted model directory:

```bash
python modeling_nebula.py .
```

## Local usage

```python
from nebula_runtime import load_model

model, tokenizer = load_model("./Nebula-S-3B")

messages = [{"role": "user", "content": "Solve: what is 2+2?"}]

if getattr(tokenizer, "chat_template", None):
    prompt = tokenizer.apply_chat_template(
        messages,
        add_generation_prompt=True,
        tokenize=False,
    )
else:
    prompt = "User: Solve: what is 2+2?\nAssistant:"

inputs = tokenizer(
    prompt,
    add_special_tokens=False,
    return_tensors="pt",
).to(next(model.parameters()).device)

text = model.generate(
    inputs["input_ids"],
    inputs["attention_mask"],
    tokenizer,
    max_new_tokens=512,
    temperature=0,
)

print(text)
```

## Creating a tuned successor release

This downloadable package is an inference artifact. To create a tuned successor release, use the approved restricted training workspace rather than modifying this folder in place.

Recommended internal flow:

1. Create a new release ID, for example `nebula_s_3b_v0_1_1`.
2. Add approved examples or correction data to the internal training dataset.
3. Train a candidate runtime artifact in the restricted training environment.
4. Compare the candidate against this release on fixed evaluation prompts and tasks.
5. Repackage the candidate with the internal packaging tool.
6. Run package validation: smoke load, leak scan, strict runtime-weight validation, checksum manifest, and license/notice review.
7. Promote only the sanitized downloadable package.

Do not upload private provenance, source training records, optimizer state, source data paths, or build logs with this package.

## License and Use Restrictions

Nebula-S-SVMS2-3B is released under the Decompute Non-Commercial Research License v1.0.

This is a restricted-access non-commercial research release. It is not an open-source release.

### Permitted Use

The model may be used only for personal, academic, and non-commercial research or evaluation.

### Prohibited Use

The model may not be used for commercial use, revenue-generating use, production use, paid API use, SaaS use, customer-facing deployment, enterprise workflow automation, redistribution, sublicensing, mirroring, uploading converted versions, uploading quantized versions, uploading fine-tuned versions, or creating/distributing derivative models.

The model and its outputs may not be used to train, improve, distill, benchmark for marketing purposes, or evaluate commercial models, products, services, or platforms.

For commercial licensing, contact hina@decompute.run.


## Evaluation Results

The following results are from Decompute internal evaluations of Nebula-S-SVMS2-3B.

| Benchmark | Score |
|---|---:|
| GPQA | 86.85 |
| HMMT Nov 2025 | 80.00 |
| GSM8K | 93.78 |
| MMLU-Pro | 83.00 |

These scores are reported from internal evaluation runs. Evaluation settings, prompts, decoding parameters, and extraction methods may affect comparability with public leaderboard results.