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
```

Ill-Ness commited on 9 days ago

Commit

0e8a062

verified ·

1 Parent(s): 6fde20b

Delete training_report.json

Browse files

Files changed (1) hide show

training_report.json +0 -37

training_report.json DELETED Viewed

@@ -1,37 +0,0 @@
-{
-  "model_name": "Supertron2-24B",
-  "base_model": "mistralai/Devstral-Small-2-24B-Instruct-2512",
-  "training_base_model": "akoumpa/Devstral-Small-2-24B-Instruct-2512-BF16",
-  "run_dir": "/artifacts/20260518-164838",
-  "adapter_dir": "/artifacts/20260518-164838/adapter",
-  "merged_dir": null,
-  "train_minutes": 60,
-  "elapsed_seconds": 181.40671366200002,
-  "global_step": 600,
-  "train_loss": 1.570858365794023,
-  "parameter_count": 24034167808,
-  "trainable_parameter_count": 22806528,
-  "attention_impl": "flash_attention_2",
-  "resumed_from": null,
-  "use_4bit": false,
-  "torch_compile": false,
-  "gradient_checkpointing": true,
-  "lora": {
-    "r": 16,
-    "alpha": 32,
-    "dropout": 0.03
-  },
-  "datasets": {
-    "SWE-bench/SWE-smith": 2000,
-    "SWE-bench/SWE-bench": 2000,
-    "ise-uiuc/Magicoder-OSS-Instruct-75K": 6000,
-    "m-a-p/CodeFeedback-Filtered-Instruction": 6000,
-    "Open-Orca/OpenOrca": 5000,
-    "HuggingFaceH4/ultrachat_200k": 5000,
-    "gsm8k": 4000,
-    "allenai/sciq": 3000,
-    "supertron2-identity": 1000
-  },
-  "pushed_to_hub": false,
-  "hub_repo_id": "Surpem/Supertron2-24B"
-}