Instructions to use Rzkoohi/Qwen2.5-4B-CCNA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Rzkoohi/Qwen2.5-4B-CCNA with Transformers:

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

pipe = pipeline("text-generation", model="Rzkoohi/Qwen2.5-4B-CCNA")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Rzkoohi/Qwen2.5-4B-CCNA")
model = AutoModelForCausalLM.from_pretrained("Rzkoohi/Qwen2.5-4B-CCNA", 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 Rzkoohi/Qwen2.5-4B-CCNA with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Rzkoohi/Qwen2.5-4B-CCNA"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Rzkoohi/Qwen2.5-4B-CCNA",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Rzkoohi/Qwen2.5-4B-CCNA

SGLang

How to use Rzkoohi/Qwen2.5-4B-CCNA 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 "Rzkoohi/Qwen2.5-4B-CCNA" \
    --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": "Rzkoohi/Qwen2.5-4B-CCNA",
		"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 "Rzkoohi/Qwen2.5-4B-CCNA" \
        --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": "Rzkoohi/Qwen2.5-4B-CCNA",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Rzkoohi/Qwen2.5-4B-CCNA with Docker Model Runner:
```
docker model run hf.co/Rzkoohi/Qwen2.5-4B-CCNA
```

Qwen2.5-1.5B-CCNA

A domain-specialized version of Qwen2.5-1.5B-Instruct, fine-tuned for Cisco CCNA concepts and networking tasks.

The model is designed to provide more accurate responses to CCNA-related questions than the base model while remaining lightweight enough to run on modest hardware.

Model Details

Property	Value
Model Name	Qwen2.5-1.5B-CCNA
Base Model	Qwen/Qwen2.5-1.5B-Instruct
Fine-tuning Method	Supervised Fine-Tuning (SFT)
Domain	Computer Networking
Specialization	Cisco CCNA
Language	English

Dataset

This model was fine-tuned using:

Dataset: Rzkoohi/CCNA_small

The dataset contains instruction-answer pairs focused on Cisco CCNA topics including:

IPv4
IPv6
Subnetting
VLANs
Trunking
Inter-VLAN Routing
STP
EtherChannel
Static Routing
OSPF
ACLs
NAT/PAT
DHCP
DNS
Cisco IOS CLI
Network Troubleshooting
General CCNA Theory

Intended Use

This model is intended for:

Cisco networking education
Cisco CLI assistance
Network troubleshooting
AI networking assistants
Educational chatbots
Local LLM deployments

Limitations

This model is specialized for Cisco CCNA topics.

While it performs well on networking questions, it may not perform as well on unrelated subjects.

Configuration examples should always be reviewed before deployment in production environments.

Training

Base Model: Qwen/Qwen2.5-1.5B-Instruct
Dataset: Rzkoohi/CCNA_small
Training Type: Supervised Fine-Tuning (SFT)

Usage

from transformers import AutoTokenizer, AutoModelForCausalLM

model_name = "Rzkoohi/Qwen2.5-4B-CCNA"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    device_map="auto"
)

messages = [
    {
        "role": "user",
        "content": "Explain OSPF Areas."
    }
]

text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
)

inputs = tokenizer(text, return_tensors="pt").to(model.device)

outputs = model.generate(
    **inputs,
    max_new_tokens=512
)

print(tokenizer.decode(outputs[0], skip_special_tokens=True))

License

This model inherits the license of the base model:

Qwen/Qwen2.5-1.5B-Instruct

Please refer to the original model license for complete terms of use.

Citation

If you use this model in research or projects, please cite:

@misc{koohi2026ccna,
  author = {Reza Koohi},
  title = {Qwen2.5-1.5B-CCNA},
  year = {2026},
  publisher = {Hugging Face},
  url = {https://huggingface.co/Rzkoohi/Qwen2.5-4B-CCNA}
}

Acknowledgements

This project is built upon the excellent Qwen2.5 foundation model developed by the Qwen Team.

Special thanks to the open-source AI community and Hugging Face for providing the ecosystem that makes projects like this possible.

⭐ If this model helps you, please consider giving it a Like on Hugging Face.

Downloads last month: -

Safetensors

Model size

2B params

Tensor type

BF16

Model tree for Rzkoohi/Qwen2.5-4B-CCNA

Base model

Qwen/Qwen2.5-1.5B

Finetuned

Qwen/Qwen2.5-1.5B-Instruct