Instructions to use dusersad12/OrionNet-Final-Checkpoint with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dusersad12/OrionNet-Final-Checkpoint with Transformers:

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

pipe = pipeline("text-generation", model="dusersad12/OrionNet-Final-Checkpoint")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("dusersad12/OrionNet-Final-Checkpoint")
model = AutoModelForCausalLM.from_pretrained("dusersad12/OrionNet-Final-Checkpoint", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use dusersad12/OrionNet-Final-Checkpoint with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "dusersad12/OrionNet-Final-Checkpoint"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "dusersad12/OrionNet-Final-Checkpoint",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/dusersad12/OrionNet-Final-Checkpoint

SGLang

How to use dusersad12/OrionNet-Final-Checkpoint 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 "dusersad12/OrionNet-Final-Checkpoint" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "dusersad12/OrionNet-Final-Checkpoint",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "dusersad12/OrionNet-Final-Checkpoint" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "dusersad12/OrionNet-Final-Checkpoint",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use dusersad12/OrionNet-Final-Checkpoint with Docker Model Runner:
```
docker model run hf.co/dusersad12/OrionNet-Final-Checkpoint
```

OrionNet

1. Introduction

OrionNet is the latest release from Stellar Labs, built on a redesigned transformer backbone that scales efficiently with data and compute. This version introduces a refined mixture-of-experts routing strategy and an expanded context window, delivering stronger multi-step reasoning while keeping inference latency comparable to dense models of similar size. Extensive internal evaluations confirm that OrionNet surpasses its predecessor across mathematics, code, and general knowledge benchmarks.

Compared to the previous OrionNet release, the current checkpoint shows markedly improved long-context handling. On the MATH-500 suite, accuracy rose from 63% to 71%, and average response length grew from 9K to 18K tokens, reflecting deeper chain-of-thought before answering. Hallucination rates on the TruthfulQA probe dropped by 12 percentage points.

Beyond reasoning, this release also ships a more robust tool-use interface and lower latency for function-calling workloads.

2. Evaluation Results

Comprehensive Benchmark Results

	Benchmark	ModelA	ModelB	ModelA-v2	OrionNet
Core Reasoning Tasks	Math Reasoning	0.412	0.445	0.460	0.627
	Logical Reasoning	0.701	0.725	0.748	0.614
	Common Sense	0.633	0.648	0.660	0.646
Language Understanding	Reading Comprehension	0.601	0.620	0.635	0.627
	Question Answering	0.488	0.499	0.503	0.507
	Text Classification	0.712	0.725	0.740	0.759
	Sentiment Analysis	0.685	0.698	0.705	0.717
Generation Tasks	Code Generation	0.520	0.545	0.560	0.567
	Creative Writing	0.495	0.505	0.510	0.495
	Dialogue Generation	0.535	0.550	0.560	0.569
	Summarization	0.660	0.675	0.685	0.677
Specialized Capabilities	Translation	0.710	0.725	0.738	0.730
	Knowledge Retrieval	0.540	0.555	0.560	0.556
	Instruction Following	0.685	0.705	0.720	0.800
	Safety Evaluation	0.650	0.680	0.695	0.746

Overall Performance Summary

OrionNet demonstrates competitive performance across all evaluated benchmark categories, with particularly strong results in instruction following and safety evaluation.

3. Chat Website & API Platform

We provide a chat interface and API for interacting with OrionNet. Please visit the Stellar Labs website for more information.

4. How to Run Locally

Please refer to our code repository for instructions on running OrionNet locally.

Key changes from the previous version:

System prompts are fully supported.
No special tokens are needed to activate the model's reasoning mode.

The architecture of OrionNet-Small matches the base model and shares the same tokenizer. It can be used as a drop-in replacement for the base model.

System Prompt

We recommend the following system prompt with a specific date.

You are OrionNet, a helpful AI assistant.
Today is {current date}.

For example,

You are OrionNet, a helpful AI assistant.
Today is March 15, 2026, Sunday.

Temperature

We recommend setting the temperature parameter $T_{model}$ to 0.7.

Prompts for File Uploading and Web Search

For file uploading, follow the template below where {file_name}, {file_content} and {question} are arguments.

file_template = \
"""[file name]: {file_name}
[file content begin]
{file_content}
[file content end]
{question}"""

For web search enhanced generation, use the following prompt template where {search_results}, {cur_date}, and {question} are arguments.

search_answer_en_template = \
'''# The following contents are the search results related to the user's message:
{search_results}
In the search results I provide to you, each result is formatted as [webpage X begin]...[webpage X end], where X represents the numerical index of each article. Please cite the context at the end of the relevant sentence when appropriate. Use the citation format [citation:X] in the corresponding part of your answer. If a sentence is derived from multiple contexts, list all relevant citation numbers, such as [citation:3][citation:5]. Be sure not to cluster all citations at the end; instead, include them in the corresponding parts of the answer.
When responding, please keep the following points in mind:
- Today is {cur_date}.
- Not all content in the search results is closely related to the user's question. You need to evaluate and filter the search results based on the question.
- For listing-type questions (e.g., listing all flight information), try to limit the answer to 10 key points and inform the user that they can refer to the search sources for complete information. Prioritize providing the most complete and relevant items in the list. Avoid mentioning content not provided in the search results unless necessary.
- For creative tasks (e.g., writing an essay), ensure that references are cited within the body of the text, such as [citation:3][citation:5], rather than only at the end of the text. You need to interpret and summarize the user's requirements, choose an appropriate format, fully utilize the search results, extract key information, and generate an answer that is insightful, creative, and professional. Extend the length of your response as much as possible, addressing each point in detail and from multiple perspectives, ensuring the content is rich and thorough.
- If the response is lengthy, structure it well and summarize it in paragraphs. If a point-by-point format is needed, try to limit it to 5 points and merge related content.
- For objective Q&A, if the answer is very brief, you may add one or two related sentences to enrich the content.
- Choose an appropriate and visually appealing format for your response based on the user's requirements and the content of the answer, ensuring strong readability.
- Your answer should synthesize information from multiple relevant webpages and avoid repeatedly citing the same webpage.
- Unless the user requests otherwise, your response should be in the same language as the user's question.
# The user's message is:
{question}'''

5. License

This code repository is licensed under the Apache 2.0 License. The use of OrionNet models is also subject to the Apache 2.0 License. The model series supports commercial use and distillation.

6. Contact

If you have any questions, please raise an issue on our GitHub repository or contact us at contact@stellar-labs.ai.

Downloads last month: 124