Instructions to use fariasultanacodes/magic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use fariasultanacodes/magic with Transformers:

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

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

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("fariasultanacodes/magic", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use fariasultanacodes/magic with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/fariasultanacodes/magic

SGLang

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

Docker Model Runner
How to use fariasultanacodes/magic with Docker Model Runner:
```
docker model run hf.co/fariasultanacodes/magic
```

magic / README.md

fariasultanacodes

Upload Magic model - Fine-tuned MMLU model by Likhon Sheikh

139857c verified 9 months ago

preview code

Raw

History Blame Contribute Delete

1.64 kB

	---
	language: en
	license: apache-2.0
	tags:
	- text-generation
	- magic
	- mmlu
	- causal-lm
	library_name: transformers
	pipeline_tag: text-generation
	base_model: Qwen/Qwen2.5-1.5B
	---

	# Magic Model 🪄

	Fine-tuned language model for MMLU-style question answering.

	Developed by Likhon Sheikh 🚀

	## Features

	- ✅ Multi-safetensor support
	- ✅ Fast tokenizer with tokenizer.json
	- ✅ LoRA fine-tuning for efficiency
	- ✅ MMLU-optimized responses
	- ✅ Production-ready deployment

	## Usage

	```python
	from transformers import AutoModelForCausalLM, AutoTokenizer

	model = AutoModelForCausalLM.from_pretrained("fariasultanacodes/magic")
	tokenizer = AutoTokenizer.from_pretrained("fariasultanacodes/magic")

	prompt = "Question: What is AI?\n\nAnswer:"
	inputs = tokenizer(prompt, return_tensors="pt")
	outputs = model.generate(**inputs, max_length=100)
	print(tokenizer.decode(outputs[0], skip_special_tokens=True))
	```

	## Pipeline Usage

	```python
	from transformers import pipeline

	generator = pipeline("text-generation", model="fariasultanacodes/magic")
	result = generator("Question: Explain machine learning.\n\nAnswer:")
	print(result[0]['generated_text'])
	```

	## Model Details

	- Base Model: Qwen/Qwen2.5-1.5B
	- Fine-tuning: LoRA adapters
	- Dataset: MMLU-style questions
	- Format: Safetensors (multi-file support)
	- Tokenizer: Fast tokenizer with JSON

	## Citation

	```bibtex
	@misc{magic-model-2025,
	title={Magic: MMLU-Optimized Language Model},
	author={Likhon Sheikh},
	year={2025},
	url={https://huggingface.co/fariasultanacodes/magic}
	}
	```

	## License

	Apache-2.0

	---

	🚀 Developed by Likhon Sheikh