Instructions to use SupraLabs/Supra2-Medium-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SupraLabs/Supra2-Medium-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="SupraLabs/Supra2-Medium-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("SupraLabs/Supra2-Medium-Instruct")
model = AutoModelForCausalLM.from_pretrained("SupraLabs/Supra2-Medium-Instruct", 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

vLLM

How to use SupraLabs/Supra2-Medium-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SupraLabs/Supra2-Medium-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SupraLabs/Supra2-Medium-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/SupraLabs/Supra2-Medium-Instruct

SGLang

How to use SupraLabs/Supra2-Medium-Instruct 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 "SupraLabs/Supra2-Medium-Instruct" \
    --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": "SupraLabs/Supra2-Medium-Instruct",
		"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 "SupraLabs/Supra2-Medium-Instruct" \
        --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": "SupraLabs/Supra2-Medium-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use SupraLabs/Supra2-Medium-Instruct with Docker Model Runner:
```
docker model run hf.co/SupraLabs/Supra2-Medium-Instruct
```

LH-Tech-AI commited on 1 day ago

Commit

b0e7665

verified ·

1 Parent(s): 200d943

Update README.md

Browse files

Files changed (1) hide show

README.md +8 -8

README.md CHANGED Viewed

@@ -14,21 +14,21 @@ tags:
 - supra2
 - qwen3
 - efficient
 ---
-<h1 align="center">Supra2-Medium Base</h1>
 <p align="center">
-  Ultra-efficient base model • 25M Parameters • 1K Context
 </p>
 ![supra2-medium](https://cdn-uploads.huggingface.co/production/uploads/697f2832c2c5e4daa93cece7/-YjDJGlcGyTN5yClAaEv3.png)
-**Supra2-Medium Base** is a 25M-parameter decoder-only language model pretrained from scratch by **SupraLabs** on 20B tokens of English web text. It uses the **Qwen3** architecture with a custom 16,384-token tokenizer.
-This is a **base model**. It has *not* been instruction-tuned, chat-tuned, or aligned in any way.
-At only 25 million parameters, Supra2-Medium demonstrates that meaningful language modeling can be achieved with extreme parameter efficiency—trained at ~800 tokens per parameter, which is significantly higher than typical pretraining ratios. This makes it ideal for research into data-efficient scaling and ultra-lightweight deployments.
 ---
@@ -140,4 +140,4 @@ print(response.strip())
 ---
-*© SupraLabs 2026*

 - supra2
 - qwen3
 - efficient
+- instruct
+- chat
+base_model:
+- SupraLabs/Supra2-Medium-Base
 ---
+<h1 align="center">Supra2-Medium Instruct</h1>
 <p align="center">
+  Ultra-efficient chat instruction model • 25M Parameters • 1K Context
 </p>
 ![supra2-medium](https://cdn-uploads.huggingface.co/production/uploads/697f2832c2c5e4daa93cece7/-YjDJGlcGyTN5yClAaEv3.png)
+**Supra2-Medium Instruct** is a 25M-parameter decoder-only language model pretrained from scratch by **SupraLabs** on 20B tokens of English web text. It uses the **Qwen3** architecture with a custom 16,384-token tokenizer. This is the instruct version of Supra2-Medium-Base.
 ---
 ---
+*© SupraLabs 2026*