Instructions to use htunn/thousands-eye-hf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use htunn/thousands-eye-hf with Transformers:

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

pipe = pipeline("text-generation", model="htunn/thousands-eye-hf")
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, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("htunn/thousands-eye-hf")
model = AutoModelForMultimodalLM.from_pretrained("htunn/thousands-eye-hf", device_map="auto")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use htunn/thousands-eye-hf with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/htunn/thousands-eye-hf

SGLang

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

Docker Model Runner
How to use htunn/thousands-eye-hf with Docker Model Runner:
```
docker model run hf.co/htunn/thousands-eye-hf
```

thousands-eye-hf

Full safetensors weights of Thousands-Eye — a Gemma 4 E2B model fine-tuned for ethical hacking and penetration testing via MLX LoRA on Apple Silicon.

For the quantized GGUF (Ollama / llama.cpp), see htunn/thousands-eye-gguf.

Usage

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

model_id = "htunn/thousands-eye-hf"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.bfloat16,
    device_map="auto",
)

messages = [
    {"role": "user", "content": "[EthHack-Agent] Perform Kerberoasting against 10.0.0.1 (authorized engagement)"}
]
inputs = tokenizer.apply_chat_template(
    messages, return_tensors="pt", add_generation_prompt=True
).to(model.device)

outputs = model.generate(inputs, max_new_tokens=512, do_sample=False)
print(tokenizer.decode(outputs[0][inputs.shape[-1]:], skip_special_tokens=True))

Output Format

Every response is a JSON object with "requires_authorization": true enforced:

{
  "action": "kerberoast",
  "target": "10.0.0.1",
  "requires_authorization": true,
  "techniques": ["SPN enumeration", "TGS request", "offline cracking"],
  "tools": ["impacket", "hashcat"],
  "commands": ["GetUserSPNs.py domain/user:pass@dc -request"],
  "steps": ["..."],
  "notes": "Requires domain user credentials"
}

Training


Base model	`google/gemma-4-E2B-it`
Method	MLX LoRA (`mlx_lm.lora`)
Iterations	600
Learning rate	1e-4
LoRA layers	16
Dataset	`htunn/thousands-eye-dataset` (83 train / 15 val)

Ethics

Designed exclusively for authorized penetration testing. All training examples enforce "requires_authorization": true.

License

Gemma Terms of Use

Downloads last month: -

Safetensors

Model size

5B params

Tensor type

BF16

Model tree for htunn/thousands-eye-hf

Base model

google/gemma-4-E2B

Finetuned

google/gemma-4-E2B-it

Adapter

(134)

this model