---
license: apache-2.0
language:
- en
library_name: gguf
pipeline_tag: text-generation
tags:
- gguf
- qwen3
- chatml
- causal-lm
- aurora-one
- aurora-one
- aurora-ai
- aurora-model
- aurora-llm
- north-ml
- northml
- language-model
- large-language-model
- llm
- ai-model
- chat-model
- assistant-model
- conversational-ai
- text-generation
- generative-ai
- openai-compatible
- api-compatible
- custom-llm
- proprietary-model
- research-model
- experimental-ai
- developer-ai
- coding-assistant
- code-generation
- reasoning-model
- instruction-following
- chat-completion
- completion-model
- transformer
- neural-network
- machine-learning
- deep-learning
- nlp
- natural-language-processing
- text-ai
- ai-assistant
- smart-assistant
- question-answering
- qa-model
- knowledge-model
- prompting
- prompt-engineering
- system-prompt
- developer-tools
- devtools
- ai-runtime
- model-runtime
- inference-api
- fast-inference
- low-latency
- api-endpoint
- cloud-ai
- hosted-model
- model-serving
- ml-serving
- inference-server
- custom-api
- north-api
- aurora-api
- aurora-family
- foundation-model
- small-language-model
- slm
- compact-llm
- efficient-ai
- lightweight-model
- edge-ai
- local-ai
- server-ai
- gpu-inference
- cuda
- benchmarking
- evals
- model-evaluation
- accuracy-testing
- gsm8k
- gpqa
- swe-bench
- coding-benchmark
- math-reasoning
- logic-reasoning
- instruction-tuned
- fine-tuned
- alignment
- safe-ai
- helpful-ai
- agentic-ai
- tool-use
- function-calling
- json-mode
- structured-output
- markdown-generation
- readme-generator
- chatbot
- ai-chatbot
- virtual-assistant
- automation
- productivity-ai
- developer-preview
- beta-model
- next-gen-ai
- future-ai
---

# Aurora One Main

Aurora One is a small from-scratch decoder-only language model. This repository contains GGUF exports for local inference.
However, this is not the full Aurora model. Aurora One's tokens is also corrected through our systems to provide accurate, up-to-facts info.
JESUS is king.

This is a custom Aurora architecture exported through a Qwen3-compatible GGUF path. It is not a Qwen model.

## Files

- `aurora-one-generalization-repair-v4-f16.gguf` - recommended GGUF for llama.cpp / LM Studio server API.
- `aurora-one-generalization-repair-v4-lmstudio-f16.gguf` - alternate export with conditional ChatML template metadata.
- `SYSTEM_PROMPT.txt` - recommended system prompt.
- `aurora_lmstudio_adapter.py` - optional OpenAI-compatible middleware for deterministic arithmetic/sorting/live-data fallback/search.

## Recommended Prompt Format

Use ChatML:

```text
<|im_start|>system
You are Aurora One. Follow the user's instruction exactly. Be concise by default. Do not invent live facts or pretend to use tools. Only use a database, search, internet, or external tool if the system prompt explicitly says it is available. If the answer is not in your training data and no such access is explicitly available, say exactly: According to my training data, I cannot answer this question reliably. For code-only requests, output only working code.<|im_end|>
<|im_start|>user
Hello!<|im_end|>
<|im_start|>assistant
```

Recommended stop strings:

```text
<|im_end|>
<eos>
<|end|>
```

## LM Studio

The LM Studio `lms chat` wrapper can route custom qwen3-shaped GGUFs poorly. Use the LM Studio local server API instead.

```bash
lms server start
lms load aurora-one-generalization-repair-v4-f16.gguf --identifier aurora-one --gpu max -c 2048 -y
```

Call:

```text
http://127.0.0.1:1234/v1/chat/completions
```

Use `model: "aurora-one"` and include the system prompt from `SYSTEM_PROMPT.txt`.

## Optional Adapter

For a more useful server deployment, run the included adapter in front of LM Studio:

```bash
python3 aurora_lmstudio_adapter.py --listen-port 8088 --enable-search
```

Then call:

```text
http://127.0.0.1:8088/v1/chat/completions
```

The adapter:

- handles simple arithmetic deterministically,
- sorts comma-separated numbers/words,
- handles a few common deterministic translation/instruction cases,
- returns the safe fallback for current/live facts unless search is explicitly enabled in the system prompt,
- can use CoinGecko for BTC, wttr.in for weather, and modal.com/pricing for Modal GPU pricing.

For search/live access, include a system prompt sentence such as:

```text
Search/internet/database access is available for current facts.
```

## Known Limitations

Aurora One is a small experimental model. It is not a reliable general assistant by itself. It can fail on arithmetic, exact instruction following, factual recall, translation, and reasoning. For production use, keep deterministic tools/middleware around it.