Instructions to use Monster-Code/Boomslang with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Monster-Code/Boomslang with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Monster-Code/Boomslang")
model = AutoModelForCausalLM.from_pretrained("Monster-Code/Boomslang", 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Monster-Code/Boomslang 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 Monster-Code/Boomslang
# Run inference directly in the terminal:
llama cli -hf Monster-Code/Boomslang

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Monster-Code/Boomslang
# Run inference directly in the terminal:
llama cli -hf Monster-Code/Boomslang

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 Monster-Code/Boomslang
# Run inference directly in the terminal:
./llama-cli -hf Monster-Code/Boomslang

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 Monster-Code/Boomslang
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Monster-Code/Boomslang

Use Docker

docker model run hf.co/Monster-Code/Boomslang

LM Studio
Jan

vLLM

How to use Monster-Code/Boomslang with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Monster-Code/Boomslang

SGLang

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

Ollama
How to use Monster-Code/Boomslang with Ollama:
```
ollama run hf.co/Monster-Code/Boomslang
```
Unsloth Desktop

How to use Monster-Code/Boomslang with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Monster-Code/Boomslang

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": "Monster-Code/Boomslang"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Monster-Code/Boomslang with Docker Model Runner:
```
docker model run hf.co/Monster-Code/Boomslang
```

Lemonade

How to use Monster-Code/Boomslang with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Monster-Code/Boomslang

Run and chat with the model

lemonade run user.Boomslang-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use Monster-Code/Boomslang with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Monster-Code/Boomslang

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 Monster-Code/Boomslang

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Monster-Code/Boomslang with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Monster-Code/Boomslang

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 "Monster-Code/Boomslang" \
  --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"

Boomslang / README.md

Monster-Code

Update README.md

258bc92 verified 5 days ago

preview code

Raw

History Blame Contribute Delete

6.16 kB

	---
	license: apache-2.0
	base_model: Qwen/Qwen2.5-3B-Instruct
	language:
	- en
	tags:
	- reasoning
	- math
	- chain-of-thought
	- qwen2.5
	- gguf
	- text-generation
	- conversational
	pipeline_tag: text-generation
	library_name: transformers
	---

	<div align="center">

	![1789911910f175](https://cdn-uploads.huggingface.co/production/uploads/6a5f8c87a38cac087c2c6c05/zZ-C-s-RZWV6sxVhj9RBe.png)

	🐍 Boomslang (3B Reasoning & Math Engine)

	A compact, high-efficiency 3-billion-parameter model fine-tuned for deep chain-of-thought mathematical reasoning, logic, and algebra—without sacrificing natural conversational ability.

	[![Hugging Face](https://img.shields.io/badge/%F0%9F%A4%97%20Creator-Monster--Code-blue)](https://huggingface.co/Monster-Code)
	[![License](https://img.shields.io/badge/License-Apache_2.0-green.svg)](https://opensource.org/licenses/Apache-2.0)
	[![GGUF Available](https://img.shields.io/badge/GGUF-Included-purple.svg)](https://huggingface.co/Monster-Code/Boomslang/blob/main/boomslang-3b-qwen.gguf)

	---

	### ❤️ If you find Boomslang useful, please hit the Like button at the top of this page and [Follow @Monster-Code](https://huggingface.co/Monster-Code) for more open-weights AI releases!

	---

	</div>

	## 💡 What is Boomslang?

	Most small models (1B–3B parameters) struggle with two extremes: they are either polite chatbots that completely hallucinate basic arithmetic, or narrow math models that forget how to hold a conversation and start writing unprompted proofs when you simply say "Hi."

	Boomslang was trained to bridge that gap.

	Starting from the strong foundation of `Qwen/Qwen2.5-3B-Instruct`, Boomslang was post-trained on an NVIDIA RTX PRO 6000 Blackwell across a curated ~17,500-sample reasoning mixture:
	1. DeepSeek-R1 Distilled Proofs (`open-r1/OpenR1-Math-220k`): Teaches the network an internal self-reflection loop (`<think> ... </think>`) to break down complex algebraic expressions, geometry, and multi-step deduction before committing to an answer.
	2. Step-by-Step Arithmetic Rigor (`openai/gsm8k`): Calibrates attention heads on strict order-of-operations arithmetic and unambiguous answer derivation.

	The result is an edge-friendly 3B model that works through tricky algebra and word puzzles methodically, but still greets you warmly and follows instructions when you just want to talk.

	---

	## 📦 What's Inside This Repository?

	* Single Standalone `model.safetensors`: No multi-part file splits. The entire 3-billion parameter model is packed into a single, clean ~6.1 GB file.
	* Pre-Converted GGUF (`boomslang-3b-qwen.gguf`): Directly ready for Ollama, LM Studio, and llama.cpp on your local machine (MacBook, laptop, or home GPU).
	* Full configuration and tokenizer files for immediate `transformers` plug-and-play.

	---

	## ⚡ Quickstart: Python & Transformers

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

	MODEL_ID = "Monster-Code/Boomslang"

	tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
	model = AutoModelForCausalLM.from_pretrained(
	MODEL_ID,
	torch_dtype=torch.bfloat16 if torch.cuda.is_available() else torch.float32,
	device_map="auto"
	)

	# Standard ChatML format
	messages = [
	{
	"role": "system",
	"content": "You are Boomslang, a helpful and precise reasoning assistant. Reason step-by-step before providing your final answer."
	},
	{
	"role": "user",
	"content": "A box has 36 chocolates. Tom eats 1/4 of them, and Sarah eats 9. How many chocolates are left in the box?"
	}
	]

	prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
	inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
	streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)

	with torch.no_grad():
	model.generate(
	**inputs,
	streamer=streamer,
	max_new_tokens=1024,
	temperature=0.6,
	top_p=0.9
	)
	```

	---

	## 💻 Running Locally with Ollama / LM Studio

	### 1. Using Ollama:
	Create a `Modelfile` in the same directory as the downloaded `.gguf`:
	```dockerfile
	FROM ./boomslang-3b-qwen.gguf

	TEMPLATE """{{ if .System }}<\|im_start\|>system
	{{ .System }}<\|im_end\|>
	{{ end }}{{ if .Prompt }}<\|im_start\|>user
	{{ .Prompt }}<\|im_end\|>
	{{ end }}<\|im_start\|>assistant
	{{ .Response }}<\|im_end\|>"""

	PARAMETER stop "<\|im_start\|>"
	PARAMETER stop "<\|im_end\|>"
	PARAMETER temperature 0.6
	```

	Build and run:
	```bash
	ollama create boomslang -f Modelfile
	ollama run boomslang
	```

	### 2. Using LM Studio:
	1. Download `boomslang-3b-qwen.gguf` from the [Files and versions tab](https://huggingface.co/Monster-Code/Boomslang/tree/main).
	2. Drop it into your local LM Studio models folder.
	3. Start chatting with GPU offloading enabled!

	---

	## 🧠 Sample Interaction

	User:
	> "Solve for x: 5x - 10 = 25. Show your work."

	Boomslang:
	```text
	<think>
	The equation is 5x - 10 = 25.
	Our goal is to isolate the variable x on one side.

	Step 1: Add 10 to both sides to cancel out the -10 constant:
	5x - 10 + 10 = 25 + 10
	5x = 35

	Step 2: Divide both sides by the coefficient 5:
	5x / 5 = 35 / 5
	x = 7

	Verification:
	Substitute x = 7 into the original expression:
	5(7) - 10 = 35 - 10 = 25.
	Both sides match.
	</think>

	The answer is x = 7.
	```

	---

	## 🛠️ Training Details

	* Base Architecture: Qwen2.5 3B (Decoder-only Transformer)
	* Hardware: NVIDIA RTX PRO 6000 Blackwell Server Edition
	* Precision: BF16 Native Mixed Precision with Fused AdamW
	* Effective Batch Size: 32 (8 per device × 4 gradient accumulation steps)
	* Learning Rate: 1.5e-4 with dynamic linear warmup
	* Label Masking: Dynamic batch padding via `DataCollatorForSeq2Seq` with `-100` masking to guarantee loss is never calculated on padding noise

	---

	## 🤝 Community & Support

	* 👤 Creator: [Monster-Code](https://huggingface.co/Monster-Code)
	* 💬 Have suggestions, evaluation runs, or dataset ideas? Leave a note in the Discussions tab!
	* ⭐ If Boomslang helps your workflow, please consider starring/liking the repository!