Instructions to use Surpem/Supertron2-24B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Surpem/Supertron2-24B with Transformers:

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

pipe = pipeline("text-generation", model="Surpem/Supertron2-24B")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("Surpem/Supertron2-24B")
model = AutoModelForImageTextToText.from_pretrained("Surpem/Supertron2-24B")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Surpem/Supertron2-24B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Surpem/Supertron2-24B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Surpem/Supertron2-24B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Surpem/Supertron2-24B

SGLang

How to use Surpem/Supertron2-24B 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 "Surpem/Supertron2-24B" \
    --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": "Surpem/Supertron2-24B",
		"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 "Surpem/Supertron2-24B" \
        --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": "Surpem/Supertron2-24B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Surpem/Supertron2-24B with Docker Model Runner:
```
docker model run hf.co/Surpem/Supertron2-24B
```

Selennnn commited on 8 days ago

Commit

c46069d

verified ·

1 Parent(s): 0e8a062

Update README.md

Browse files

Files changed (1) hide show

README.md +0 -13

README.md CHANGED Viewed

@@ -26,7 +26,6 @@ tags:
 * **Developed by:** Surpem
 * **Model type:** Causal Language Model
 * **Architecture:** Dense Transformer, 24B parameters
-* **Fine-tuned from:** [mistralai/Devstral-Small-2-24B-Instruct-2512](https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512)
 * **License:** Apache 2.0
 ---
@@ -55,17 +54,6 @@ Supertron2-24B can assist with writing, brainstorming, explanations, planning, s
 ---
-## **Evaluation**
-Supertron2-24B has been tested on a 1,000-sample MMLU-Pro preview run.
-| Benchmark | Split | Samples | Score |
-|---|---:|---:|---:|
-| MMLU-Pro | test | 1,000 | 38.5% |
-This preview run used the merged checkpoint and deterministic multiple-choice generation.
----
 ## **Get Started**
@@ -125,7 +113,6 @@ Supertron2-24B is intended for:
 * It may produce incorrect code, incomplete reasoning, or outdated information.
 * It should not be used as the only source for medical, legal, financial, or safety-critical decisions.
 * Generated code should be reviewed and tested before use.
-* Benchmark results can vary depending on prompt format, decoding settings, and evaluation harness.
 ---

 * **Developed by:** Surpem
 * **Model type:** Causal Language Model
 * **Architecture:** Dense Transformer, 24B parameters
 * **License:** Apache 2.0
 ---
 ---
 ## **Get Started**
 * It may produce incorrect code, incomplete reasoning, or outdated information.
 * It should not be used as the only source for medical, legal, financial, or safety-critical decisions.
 * Generated code should be reviewed and tested before use.
 ---