Instructions to use CyberNative-AI/Colibri_8b_v0.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use CyberNative-AI/Colibri_8b_v0.1 with Transformers:

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

pipe = pipeline("text-generation", model="CyberNative-AI/Colibri_8b_v0.1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("CyberNative-AI/Colibri_8b_v0.1")
model = AutoModelForCausalLM.from_pretrained("CyberNative-AI/Colibri_8b_v0.1", 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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use CyberNative-AI/Colibri_8b_v0.1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "CyberNative-AI/Colibri_8b_v0.1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "CyberNative-AI/Colibri_8b_v0.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/CyberNative-AI/Colibri_8b_v0.1

SGLang

How to use CyberNative-AI/Colibri_8b_v0.1 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 "CyberNative-AI/Colibri_8b_v0.1" \
    --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": "CyberNative-AI/Colibri_8b_v0.1",
		"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 "CyberNative-AI/Colibri_8b_v0.1" \
        --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": "CyberNative-AI/Colibri_8b_v0.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use CyberNative-AI/Colibri_8b_v0.1 with Docker Model Runner:
```
docker model run hf.co/CyberNative-AI/Colibri_8b_v0.1
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Llama 3 Colibri 8B v0.1

Built with Meta Llama 3

Repository records previously reported Dolphin 2.9 Llama 3 8B as the upstream model for Llama 3 Colibri 8B v0.1. CyberNative AI cannot currently verify that lineage from a primary training or weight-lineage record.

The companion Q5 GGUF is available at CyberNative-AI/Llama-3-Colibri-8B-v0.1-Q5-GGUF.

Provenance limitation

This card previously claimed a training corpus of around 35k Q/A pairs derived from cybersecurity-related texts. CyberNative AI cannot currently evidence the source corpus, source URLs, rights holders, licenses, or transformation records for those pairs. Provenance is unverified. Do not infer a rights basis for those pairs from this card.

Known-risk and acceptable-use notice

The repository previously reported Dolphin 2.9 Llama 3 8B as upstream, but that lineage is currently unverified. Its public model card describes it as uncensored; conservatively, this model may produce unsafe, inaccurate, or inappropriate cybersecurity content. Do not use it for illegal, malicious, or harmful activity. Use of Meta Llama 3 is subject to the Meta Llama 3 Acceptable Use Policy.

License and notice

The Meta Llama 3 Community License Agreement is distributed with this repository. The required attribution is in NOTICE.

This model uses the ChatML prompt template format:

<|im_start|>system
You are Colibri, an advanced cybersecurity AI assistant developed by CyberNative AI.<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant

Provided by CyberNative AI