Instructions to use Refract-Labs/Orion-Flagship-Mini with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Refract-Labs/Orion-Flagship-Mini with Transformers:

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

pipe = pipeline("text-generation", model="Refract-Labs/Orion-Flagship-Mini", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("Refract-Labs/Orion-Flagship-Mini", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Refract-Labs/Orion-Flagship-Mini with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Refract-Labs/Orion-Flagship-Mini

SGLang

How to use Refract-Labs/Orion-Flagship-Mini 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 "Refract-Labs/Orion-Flagship-Mini" \
    --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": "Refract-Labs/Orion-Flagship-Mini",
		"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 "Refract-Labs/Orion-Flagship-Mini" \
        --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": "Refract-Labs/Orion-Flagship-Mini",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Refract-Labs/Orion-Flagship-Mini with Docker Model Runner:
```
docker model run hf.co/Refract-Labs/Orion-Flagship-Mini
```

Orion-Flagship-Mini / README.md

Bc-AI

Update README.md

96ad5fe verified about 1 month ago

preview code

Raw History Blame Contribute Delete

2.25 kB

---
library_name: transformers
pipeline_tag: text-generation
license: other
license_name: orion-t2-research
tags:
- project-prism
- orion
- orion-t2
- custom-code
- causal-lm
- instruction-tuned
- conversational
base_model: Project-Prism/Orion-Flagship-Mini-Preview
---
# 🔺 Orion T2 Mini SFT

**Orion T2 Mini SFT** is the supervised-fine-tuned assistant variant of Project Prism's experimental Orion T2 architecture.

It starts from the completed Orion T2 Mini base checkpoint and was then trained with response-only SFT on 700,000 examples: 60% general/conversation, 20% math, and 20% code.

## Chat format

Use the bundled Hugging Face chat template. The model was trained with literal text role markers `<|system|>`, `<|user|>`, and `<|assistant|>`. Those markers were **not** added as new tokenizer special tokens.

```python
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
repo = "Project-Prism/Orion-Flagship-Mini-SFT"
tokenizer = AutoTokenizer.from_pretrained(repo, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    repo, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map="auto"
)
messages = [
    {"role": "system", "content": "You are Orion, a helpful AI assistant."},
    {"role": "user", "content": "Explain why the sky is blue."},
]
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
with torch.inference_mode():
    output = model.generate(**inputs, max_new_tokens=128, temperature=0.7, top_p=0.95, do_sample=True, use_cache=False)
new_tokens = output[0, inputs["input_ids"].shape[1]:]
print(tokenizer.decode(new_tokens, skip_special_tokens=True))
```

## Architecture

Orion T2 Mini has approximately 219M total parameters and combines a 12-stage Universal Cortex, shared sparse Procedure Banks, a sparse Knowledge Vault, explicit Working State, and recurrent late-stage deliberation.

The current Transformers compatibility layer uses `use_cache=False`, so generation recomputes the prefix each token.

## Status

Experimental Project Prism research model. Architecture claims should be judged with matched evaluations rather than assumed from the design alone.

	---
	library_name: transformers
	pipeline_tag: text-generation
	license: other
	license_name: orion-t2-research
	tags:
	- project-prism
	- orion
	- orion-t2
	- custom-code
	- causal-lm
	- instruction-tuned
	- conversational
	base_model: Project-Prism/Orion-Flagship-Mini-Preview
	---

	# 🔺 Orion T2 Mini SFT

	Orion T2 Mini SFT is the supervised-fine-tuned assistant variant of Project Prism's experimental Orion T2 architecture.

	It starts from the completed Orion T2 Mini base checkpoint and was then trained with response-only SFT on 700,000 examples: 60% general/conversation, 20% math, and 20% code.

	## Chat format

	Use the bundled Hugging Face chat template. The model was trained with literal text role markers `<\|system\|>`, `<\|user\|>`, and `<\|assistant\|>`. Those markers were not added as new tokenizer special tokens.

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

	repo = "Project-Prism/Orion-Flagship-Mini-SFT"
	tokenizer = AutoTokenizer.from_pretrained(repo, trust_remote_code=True)
	model = AutoModelForCausalLM.from_pretrained(
	repo, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map="auto"
	)
	messages = [
	{"role": "system", "content": "You are Orion, a helpful AI assistant."},
	{"role": "user", "content": "Explain why the sky is blue."},
	]
	prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
	inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
	with torch.inference_mode():
	output = model.generate(**inputs, max_new_tokens=128, temperature=0.7, top_p=0.95, do_sample=True, use_cache=False)
	new_tokens = output[0, inputs["input_ids"].shape[1]:]
	print(tokenizer.decode(new_tokens, skip_special_tokens=True))
	```

	## Architecture

	Orion T2 Mini has approximately 219M total parameters and combines a 12-stage Universal Cortex, shared sparse Procedure Banks, a sparse Knowledge Vault, explicit Working State, and recurrent late-stage deliberation.

	The current Transformers compatibility layer uses `use_cache=False`, so generation recomputes the prefix each token.

	## Status

	Experimental Project Prism research model. Architecture claims should be judged with matched evaluations rather than assumed from the design alone.