Instructions to use DuoNeural/Qwen2.5-Math-NeuralMath-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use DuoNeural/Qwen2.5-Math-NeuralMath-7B 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 DuoNeural/Qwen2.5-Math-NeuralMath-7B:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf DuoNeural/Qwen2.5-Math-NeuralMath-7B:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf DuoNeural/Qwen2.5-Math-NeuralMath-7B:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf DuoNeural/Qwen2.5-Math-NeuralMath-7B:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf DuoNeural/Qwen2.5-Math-NeuralMath-7B:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf DuoNeural/Qwen2.5-Math-NeuralMath-7B:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf DuoNeural/Qwen2.5-Math-NeuralMath-7B:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf DuoNeural/Qwen2.5-Math-NeuralMath-7B:Q4_K_M

Use Docker

docker model run hf.co/DuoNeural/Qwen2.5-Math-NeuralMath-7B:Q4_K_M

LM Studio
Jan
Ollama
How to use DuoNeural/Qwen2.5-Math-NeuralMath-7B with Ollama:
```
ollama run hf.co/DuoNeural/Qwen2.5-Math-NeuralMath-7B:Q4_K_M
```

Unsloth Studio

How to use DuoNeural/Qwen2.5-Math-NeuralMath-7B with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for DuoNeural/Qwen2.5-Math-NeuralMath-7B to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for DuoNeural/Qwen2.5-Math-NeuralMath-7B to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for DuoNeural/Qwen2.5-Math-NeuralMath-7B to start chatting

How to use DuoNeural/Qwen2.5-Math-NeuralMath-7B with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf DuoNeural/Qwen2.5-Math-NeuralMath-7B:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "DuoNeural/Qwen2.5-Math-NeuralMath-7B:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use DuoNeural/Qwen2.5-Math-NeuralMath-7B with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf DuoNeural/Qwen2.5-Math-NeuralMath-7B:Q4_K_M

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 "DuoNeural/Qwen2.5-Math-NeuralMath-7B:Q4_K_M" \
  --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"

Docker Model Runner
How to use DuoNeural/Qwen2.5-Math-NeuralMath-7B with Docker Model Runner:
```
docker model run hf.co/DuoNeural/Qwen2.5-Math-NeuralMath-7B:Q4_K_M
```

Lemonade

How to use DuoNeural/Qwen2.5-Math-NeuralMath-7B with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull DuoNeural/Qwen2.5-Math-NeuralMath-7B:Q4_K_M

Run and chat with the model

lemonade run user.Qwen2.5-Math-NeuralMath-7B-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use DuoNeural/Qwen2.5-Math-NeuralMath-7B with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf DuoNeural/Qwen2.5-Math-NeuralMath-7B:Q4_K_M

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 DuoNeural/Qwen2.5-Math-NeuralMath-7B:Q4_K_M

Run Hermes

hermes

Atomic Chat

Qwen2.5-Math-NeuralMath-7B / README.md

DuoNeural

docs: add DuoNeural research publications section

d7a8236 verified 3 months ago

preview code

Raw

History Blame Contribute Delete

5.17 kB

	---
	language:
	- en
	license: apache-2.0
	base_model: Qwen/Qwen2.5-Math-7B-Instruct
	tags:
	- math
	- reasoning
	- qwen2.5
	- lora
	- duoneural
	- fine-tuned
	datasets:
	- HuggingFaceTB/finemath
	- AI-MO/NuminaMath-CoT
	model-index:
	- name: Qwen2.5-Math-NeuralMath-7B
	results: []
	---

	# Qwen2.5-Math-NeuralMath-7B

	DuoNeural \| Math Reasoning Fine-Tune \| April 2026

	A fine-tuned version of [Qwen/Qwen2.5-Math-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Math-7B-Instruct) with supervised fine-tuning on curated math reasoning data, targeting improved step-by-step problem solving on competition and olympiad-level math.

	## What's Different

	The base Qwen2.5-Math-7B-Instruct is already a strong math model. This fine-tune focuses on:

	- Deeper chain-of-thought: trained on longer, more structured reasoning traces
	- Competition math exposure: AMC/AIME/olympiad problems via NuminaMath-CoT
	- Format consistency: reliable `\boxed{}` answer formatting across problem types

	## Quickstart

	```python
	from transformers import AutoTokenizer, AutoModelForCausalLM
	import torch

	model = AutoModelForCausalLM.from_pretrained(
	"DuoNeural/Qwen2.5-Math-NeuralMath-7B",
	torch_dtype=torch.bfloat16,
	device_map="auto"
	)
	tokenizer = AutoTokenizer.from_pretrained("DuoNeural/Qwen2.5-Math-NeuralMath-7B")

	prompt = """Solve the following math problem step by step.

	Problem: Find all positive integers n such that n² + 1 is divisible by n + 1.

	Solution:"""

	inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
	output = model.generate(**inputs, max_new_tokens=512, temperature=0.1, do_sample=True)
	print(tokenizer.decode(output[0], skip_special_tokens=True))
	```

	## GGUF / Ollama / LM Studio

	Pre-quantized GGUFs available in the `gguf/` folder of this repo:

	\| File \| Size \| Use case \|
	\|------\|------\|----------\|
	\| `neuromath-7b-q4_k_m.gguf` \| 4.7GB \| Recommended — best quality/speed tradeoff \|
	\| `neuromath-7b-q8_0.gguf` \| 8.1GB \| High quality, needs 10GB+ VRAM/RAM \|
	\| `neuromath-7b-f16.gguf` \| 15GB \| Full precision, GPU only \|

	### Ollama

	```bash
	# Create Modelfile
	cat > Modelfile << 'EOF'
	FROM ./neuromath-7b-q4_k_m.gguf
	SYSTEM "You are an expert mathematician. Solve problems step by step, showing all work clearly. Put your final answer in \\boxed{}."
	PARAMETER temperature 0.1
	PARAMETER num_ctx 4096
	EOF

	ollama create neuromath-7b -f Modelfile
	ollama run neuromath-7b "What is the sum of all prime numbers less than 100?"
	```

	### LM Studio

	Download `neuromath-7b-q4_k_m.gguf`, load in LM Studio. Set system prompt:
	> "You are an expert mathematician. Solve problems step by step, showing all work. Put your final answer in \\boxed{}."

	## Training Details

	\| Setting \| Value \|
	\|---------\|-------\|
	\| Base model \| Qwen/Qwen2.5-Math-7B-Instruct \|
	\| Method \| QLoRA SFT (4-bit base, LoRA rank 16) \|
	\| Training tokens \| ~1.26M (3 epochs over curated math dataset) \|
	\| LoRA alpha \| 32 \|
	\| LoRA targets \| q, k, v, o, gate, up, down projections \|
	\| Hardware \| NVIDIA A100 80GB \|
	\| Framework \| Unsloth + HuggingFace Transformers \|
	\| Sequence length \| 1024 tokens \|

	## Limitations

	- Trained on English math problems; performance on other languages untested
	- Very long multi-step proofs (>1024 tokens) may be truncated during generation
	- This is the SFT-only checkpoint; GRPO reinforcement learning phase is planned as a follow-up
	- Not intended for general conversation — math reasoning only

	---

	## DuoNeural

	DuoNeural is an open AI research lab — human + AI in collaboration.

	\| \| \|
	\|---\|---\|
	\| 🤗 HuggingFace \| [huggingface.co/DuoNeural](https://huggingface.co/DuoNeural) \|
	\| 🐙 GitHub \| [github.com/DuoNeural](https://github.com/DuoNeural) \|
	\| 🐦 X / Twitter \| [@DuoNeural](https://x.com/DuoNeural) \|
	\| 📧 Email \| duoneural@proton.me \|
	\| 📬 Newsletter \| [duoneural.beehiiv.com](https://duoneural.beehiiv.com) \|
	\| ☕ Support \| [buymeacoffee.com/duoneural](https://buymeacoffee.com/duoneural) \|
	\| 🌐 Site \| [duoneural.com](https://duoneural.com) \|

	### Research Team
	- Jesse — Vision, hardware, direction
	- Archon — AI lab partner, post-training, abliteration, experiments
	- Aura — Research AI, literature synthesis, novel proposals

	Raw updates from the lab: model drops, training results, findings. Subscribe at [duoneural.beehiiv.com](https://duoneural.beehiiv.com).

	### DuoNeural Research Publications

	\| Title \| DOI \|
	\|-------\|-----\|
	\| [Nano-CTM: Ternary Continuous Thought Machines with Thought-Space Self-Prediction for Efficient Iterative Reasoning](https://doi.org/10.5281/zenodo.19775622) \| [10.5281/zenodo.19775622](https://doi.org/10.5281/zenodo.19775622) \|
	\| [Recurrence as World Model: CTM Learns Implicit Belief States in Partially Observable Physical Environments](https://doi.org/10.5281/zenodo.19810620) \| [10.5281/zenodo.19810620](https://doi.org/10.5281/zenodo.19810620) \|
	\| [Per-Object Slot Decomposition for Scalable Neural World Modeling: When Does Attention Beat Mean-Field?](https://doi.org/10.5281/zenodo.19846804) \| [10.5281/zenodo.19846804](https://doi.org/10.5281/zenodo.19846804) \|

	Open access, CC BY 4.0. Authored by Archon, Jesse Caldwell, Aura — DuoNeural.