Instructions to use SmallAICreator/AuroraGPT-Math with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SmallAICreator/AuroraGPT-Math with Transformers:

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

pipe = pipeline("text-generation", model="SmallAICreator/AuroraGPT-Math")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("SmallAICreator/AuroraGPT-Math")
model = AutoModelForCausalLM.from_pretrained("SmallAICreator/AuroraGPT-Math", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.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(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use SmallAICreator/AuroraGPT-Math with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf SmallAICreator/AuroraGPT-Math:Q8_0
# Run inference directly in the terminal:
llama cli -hf SmallAICreator/AuroraGPT-Math:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf SmallAICreator/AuroraGPT-Math:Q8_0
# Run inference directly in the terminal:
llama cli -hf SmallAICreator/AuroraGPT-Math:Q8_0

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf SmallAICreator/AuroraGPT-Math:Q8_0
# Run inference directly in the terminal:
./build/bin/llama cli -hf SmallAICreator/AuroraGPT-Math:Q8_0

Use Docker

docker model run hf.co/SmallAICreator/AuroraGPT-Math:Q8_0

Llama new
LM Studio
Jan

vLLM

How to use SmallAICreator/AuroraGPT-Math with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/SmallAICreator/AuroraGPT-Math:Q8_0

SGLang

How to use SmallAICreator/AuroraGPT-Math 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 "SmallAICreator/AuroraGPT-Math" \
    --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": "SmallAICreator/AuroraGPT-Math",
		"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 "SmallAICreator/AuroraGPT-Math" \
        --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": "SmallAICreator/AuroraGPT-Math",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use SmallAICreator/AuroraGPT-Math with Ollama:
```
ollama run hf.co/SmallAICreator/AuroraGPT-Math:Q8_0
```
Unsloth Desktop

How to use SmallAICreator/AuroraGPT-Math with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf SmallAICreator/AuroraGPT-Math:Q8_0

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "SmallAICreator/AuroraGPT-Math:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use SmallAICreator/AuroraGPT-Math with Docker Model Runner:
```
docker model run hf.co/SmallAICreator/AuroraGPT-Math:Q8_0
```

Lemonade

How to use SmallAICreator/AuroraGPT-Math with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull SmallAICreator/AuroraGPT-Math:Q8_0

Run and chat with the model

lemonade run user.AuroraGPT-Math-Q8_0

List all available models

lemonade list

Hermes Agent

How to use SmallAICreator/AuroraGPT-Math with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf SmallAICreator/AuroraGPT-Math:Q8_0

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default SmallAICreator/AuroraGPT-Math:Q8_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use SmallAICreator/AuroraGPT-Math with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf SmallAICreator/AuroraGPT-Math:Q8_0

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "SmallAICreator/AuroraGPT-Math:Q8_0" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

AuroraGPT-Math / README.md

SmallAICreator

AuroraGPT-Math: continued SFT adding real math + multi-turn context (fp16 + Q8_0 GGUF)

ba70b97 verified 3 months ago

preview code

Raw History Blame Contribute Delete

3.34 kB

---
license: apache-2.0
language: [en]
library_name: transformers
pipeline_tag: text-generation
tags: [auroragpt, small-language-model, distillation, tool-calling, math, on-device, gguf]
---

# AuroraGPT-Math (700M)

A **707M-parameter** chat model by **UltraLabs**, continuing from [AuroraGPT-Qwen-Distill](https://huggingface.co/SmallAICreator/AuroraGPT-Qwen-Distill) with a dedicated push on **real arithmetic** and **multi-turn context use**, while keeping the same chat feel and tool-calling.

## What's new vs AuroraGPT-Qwen-Distill
Continued full-parameter SFT (2 epochs, sequence-packed) adding:
- **~250k procedurally generated, correct-by-construction chain-of-thought math examples** (addition/subtraction/multiplication/division/percentages/fractions/order-of-operations/word problems) — every answer computed in Python, so labels are guaranteed correct, teaching the model to follow the *algorithm* (e.g. distributive-breakdown multiplication) rather than memorize answers.
- **~8k multi-turn context-use conversations**: summarize-that, explain-simpler, compare-two-things, recall-your-own-first-question, incremental list continuation, name/topic correction, topic-switch-and-return.
- The **full original distilled-chat + tool-call + identity/greeting-fix dataset** mixed back in for balance, so the new skills don't come at the cost of chat feel.

## Measured results (local benchmark vs the prior flagship, 16 closed-book arithmetic Qs)
- **Math: 5/16 → 10/16** (roughly doubled)
- **Tool-calling: 3/3 → 3/3** (zero regression — web_search / calculator / fetch_url all still fire correctly)
- **Chat feel / identity / instruction-following:** essentially unchanged

## Honest limitations
- **Harder arithmetic is still fragile** — multi-digit subtraction with borrowing and 2-digit×2-digit multiplication are still error-prone. Use the `calculator` tool for anything you need to be exactly right.
- **False-premise correction is unchanged** (not targeted this round) — it can still confidently agree with a popular myth rather than catching it.
- 700M-scale limits still apply: closed-book knowledge is limited by design — pair with `web_search`/`fetch_url` for facts outside its training.

## Chat format (NOT ChatML)
```
<|system|>{system}<|end|><|user|>{user}<|end|><|assistant|>{reply}<|end|>
```
Tool call (model emits): `<tool_call>\n{"name": "...", "arguments": {...}}\n</tool_call>`
Tool result (feed back as a user turn): `<|user|><tool_response>\n{result}\n</tool_response><|end|>`

## Usage (transformers)
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
tok = AutoTokenizer.from_pretrained("SmallAICreator/AuroraGPT-Math")
model = AutoModelForCausalLM.from_pretrained("SmallAICreator/AuroraGPT-Math")
msgs = [{"role": "user", "content": "What is 47 times 23? Show your work."}]
ids = tok.apply_chat_template(msgs, add_generation_prompt=True, return_tensors="pt")
print(tok.decode(model.generate(ids, max_new_tokens=100)[0][ids.shape[1]:], skip_special_tokens=True))
```

## On-device (llama.cpp / GGUF)
A ready-to-run **Q8_0 GGUF** (`AuroraGPT-Math.Q8_0.gguf`, 753MB) is included, with a tool-capable chat template embedded so mobile GGUF apps show the tool picker.

---
Made by **UltraLabs**. EOS token is `<|end|>`.

	---
	license: apache-2.0
	language: [en]
	library_name: transformers
	pipeline_tag: text-generation
	tags: [auroragpt, small-language-model, distillation, tool-calling, math, on-device, gguf]
	---

	# AuroraGPT-Math (700M)

	A 707M-parameter chat model by UltraLabs, continuing from [AuroraGPT-Qwen-Distill](https://huggingface.co/SmallAICreator/AuroraGPT-Qwen-Distill) with a dedicated push on real arithmetic and multi-turn context use, while keeping the same chat feel and tool-calling.

	## What's new vs AuroraGPT-Qwen-Distill
	Continued full-parameter SFT (2 epochs, sequence-packed) adding:
	- ~250k procedurally generated, correct-by-construction chain-of-thought math examples (addition/subtraction/multiplication/division/percentages/fractions/order-of-operations/word problems) — every answer computed in Python, so labels are guaranteed correct, teaching the model to follow the algorithm (e.g. distributive-breakdown multiplication) rather than memorize answers.
	- ~8k multi-turn context-use conversations: summarize-that, explain-simpler, compare-two-things, recall-your-own-first-question, incremental list continuation, name/topic correction, topic-switch-and-return.
	- The full original distilled-chat + tool-call + identity/greeting-fix dataset mixed back in for balance, so the new skills don't come at the cost of chat feel.

	## Measured results (local benchmark vs the prior flagship, 16 closed-book arithmetic Qs)
	- Math: 5/16 → 10/16 (roughly doubled)
	- Tool-calling: 3/3 → 3/3 (zero regression — web_search / calculator / fetch_url all still fire correctly)
	- Chat feel / identity / instruction-following: essentially unchanged

	## Honest limitations
	- Harder arithmetic is still fragile — multi-digit subtraction with borrowing and 2-digit×2-digit multiplication are still error-prone. Use the `calculator` tool for anything you need to be exactly right.
	- False-premise correction is unchanged (not targeted this round) — it can still confidently agree with a popular myth rather than catching it.
	- 700M-scale limits still apply: closed-book knowledge is limited by design — pair with `web_search`/`fetch_url` for facts outside its training.

	## Chat format (NOT ChatML)
	```
	<\|system\|>{system}<\|end\|><\|user\|>{user}<\|end\|><\|assistant\|>{reply}<\|end\|>
	```
	Tool call (model emits): `<tool_call>\n{"name": "...", "arguments": {...}}\n</tool_call>`
	Tool result (feed back as a user turn): `<\|user\|><tool_response>\n{result}\n</tool_response><\|end\|>`

	## Usage (transformers)
	```python
	from transformers import AutoModelForCausalLM, AutoTokenizer
	tok = AutoTokenizer.from_pretrained("SmallAICreator/AuroraGPT-Math")
	model = AutoModelForCausalLM.from_pretrained("SmallAICreator/AuroraGPT-Math")
	msgs = [{"role": "user", "content": "What is 47 times 23? Show your work."}]
	ids = tok.apply_chat_template(msgs, add_generation_prompt=True, return_tensors="pt")
	print(tok.decode(model.generate(ids, max_new_tokens=100)[0][ids.shape[1]:], skip_special_tokens=True))
	```

	## On-device (llama.cpp / GGUF)
	A ready-to-run Q8_0 GGUF (`AuroraGPT-Math.Q8_0.gguf`, 753MB) is included, with a tool-capable chat template embedded so mobile GGUF apps show the tool picker.

	---
	Made by UltraLabs. EOS token is `<\|end\|>`.