Instructions to use NovatasticRoScript/Atomight-2-1.5B-Thinking with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use NovatasticRoScript/Atomight-2-1.5B-Thinking with Transformers:

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

pipe = pipeline("text-generation", model="NovatasticRoScript/Atomight-2-1.5B-Thinking")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("NovatasticRoScript/Atomight-2-1.5B-Thinking")
model = AutoModelForCausalLM.from_pretrained("NovatasticRoScript/Atomight-2-1.5B-Thinking")
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

vLLM

How to use NovatasticRoScript/Atomight-2-1.5B-Thinking with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "NovatasticRoScript/Atomight-2-1.5B-Thinking"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "NovatasticRoScript/Atomight-2-1.5B-Thinking",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/NovatasticRoScript/Atomight-2-1.5B-Thinking

SGLang

How to use NovatasticRoScript/Atomight-2-1.5B-Thinking 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 "NovatasticRoScript/Atomight-2-1.5B-Thinking" \
    --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": "NovatasticRoScript/Atomight-2-1.5B-Thinking",
		"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 "NovatasticRoScript/Atomight-2-1.5B-Thinking" \
        --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": "NovatasticRoScript/Atomight-2-1.5B-Thinking",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio new

How to use NovatasticRoScript/Atomight-2-1.5B-Thinking 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 NovatasticRoScript/Atomight-2-1.5B-Thinking 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 NovatasticRoScript/Atomight-2-1.5B-Thinking to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for NovatasticRoScript/Atomight-2-1.5B-Thinking to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="NovatasticRoScript/Atomight-2-1.5B-Thinking",
    max_seq_length=2048,
)

Docker Model Runner
How to use NovatasticRoScript/Atomight-2-1.5B-Thinking with Docker Model Runner:
```
docker model run hf.co/NovatasticRoScript/Atomight-2-1.5B-Thinking
```

Atomight-2-1.5B-Thinking / README.md

NovatasticRoScript

Update README.md

1f7c0e7 verified 2 days ago

preview code

raw

history blame contribute delete

4.11 kB

	---
	license: mit
	base_model: NovatasticRoScript/Atomight-2-1.5B-Thinking
	tags:
	- text-generation-inference
	- transformers
	- unsloth
	- reasoning
	- thought
	- core-math
	- instruction-tuning
	model_creator: NovatasticRoScript
	model_type: causal-lm
	language:
	- en
	pipeline_tag: text-generation
	---

	<div align="center">

	# ⚛️ Atomight-2-1.5B-Thinking

	A Deep-Reasoning Small Language Model Optimized for Sequential Logic Chains

	</div>

	## 📌 Model Overview
	Atomight-2-1.5B-Thinking is a specialized, compact reasoning model built on top of a 1.5B parameter core architecture. Engineered explicitly for users operating on constrained hardware environments (such as a free Google Colab T4 instance), Atomight-2 utilizes an explicit internal `<think>...</think>` scratchpad layout. It dynamically breaks down complex mathematical, logical, and structural prompts before committing to a final conclusion.

	### 🚀 Key Highlights
	* Hardware Democratic: High-tier deep reasoning accessible on consumer-grade hardware and free cloud compute tiers.
	* Structured Scratchpad: Generates native, visible reasoning pathways natively formatted for transparent auditing.
	* Chat-Template Native: Tailored directly for ChatML system configurations.

	---

	## 📊 Evaluation & Benchmark Results

	Atomight-2 was subjected to a high-volume statistical evaluation matrix across core logic paradigms, matching up against premier industry baselines in the 1B–4B small language model class.

	### Official Performance Breakdown
	The model displays exceptional specialization spikes in structured mathematical deduction, rivaling or outperforming significantly larger parameters classes on core numerical strings.

	<div align="center">
	<img src="https://huggingface.co/NovatasticRoScript/Atomight-2-1.5B-Thinking/resolve/main/Note%20Original%20benchmarking%20of%20Atomight-2-1.5B-Thinking%20consists%20of.png" alt="Atomight-2 Official Benchmark Result" width="85%">
	</div>

	\| Benchmark \| Paradigm \| Atomight-2-1.5B-Thinking \| Qwen-2-1.5B-Instruct \| Phi-3-mini (3.8B) \| Llama-3.2-3B-Instruct \|
	\| :--- \| :--- \| :---: \| :---: \| :---: \| :---: \|
	\| GSM8k \| Math Logical Chains \| 80.1% \| 71.0% \| 82.5% \| 73.1% \|
	\| ARC-C \| Core Reasoning \| 88.5% \| 82.3% \| 84.9% \| 83.3% \|
	\| MMLU \| General Knowledge \| 63.2% \| 56.7% \| 68.8% \| 61.1% \|

	> ⚠️ Evaluation Insight: While Atomight-2 exhibits class-leading spikes on core textual logic and mathematical proofs, it experiences a classic reasoning tradeoff. On abstract matrix-grid visual transformation evaluations (like ARC-AGI 2), it drops to a baseline floor of 0.00%. This cognitive bottleneck highlights an instruction deficit in translating spatial imagery into basic structural text tokens—a major priority slated for the next architecture generation.

	---

	## 💻 Quickstart & Inference Code

	To deploy Atomight-2 cleanly without encountering text-truncation errors inside the internal reasoning blocks, execute the generation using the official structured chat template format.

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

	MODEL_ID = "NovatasticRoScript/Atomight-2-1.5B-Thinking"

	tokenizer = AutoTokenizer.from_pretrained(MODEL_ID, trust_remote_code=True)
	model = AutoModelForCausalLM.from_pretrained(
	MODEL_ID,
	torch_dtype=torch.float16,
	device_map="auto",
	trust_remote_code=True
	)

	# Structure conversational dialog into ChatML framework
	messages = [
	{"role": "user", "content": "A retailer buys shirts for $15 and sells them for $25. What is the total profit on 12 shirts?"}
	]

	templated_input = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
	inputs = tokenizer(templated_input, return_tensors="pt").to("cuda")

	print("🧠 Generating Reasoning Sequence:")
	outputs = model.generate(
	**inputs,
	max_new_tokens=768, # Plentiful headroom required for deep-thinking scratchpads
	temperature=0.1,
	do_sample=False,
	pad_token_id=tokenizer.eos_token_id
	)

	print(tokenizer.decode(outputs[0], skip_special_tokens=False))