Instructions to use squ11z1/Mythoseek with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use squ11z1/Mythoseek with Transformers:

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

pipe = pipeline("image-text-to-text", model="squ11z1/Mythoseek")
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("squ11z1/Mythoseek")
model = AutoModelForImageTextToText.from_pretrained("squ11z1/Mythoseek")
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

vLLM

How to use squ11z1/Mythoseek with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "squ11z1/Mythoseek"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "squ11z1/Mythoseek",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/squ11z1/Mythoseek

SGLang

How to use squ11z1/Mythoseek 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 "squ11z1/Mythoseek" \
    --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": "squ11z1/Mythoseek",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "squ11z1/Mythoseek" \
        --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": "squ11z1/Mythoseek",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use squ11z1/Mythoseek with Docker Model Runner:
```
docker model run hf.co/squ11z1/Mythoseek
```

squ11z1 commited on 3 days ago

Commit

2981625

verified ·

1 Parent(s): 805ac77

Update README.md with full model card

Browse files

Files changed (1) hide show

README.md +98 -3

README.md CHANGED Viewed

@@ -1,8 +1,103 @@
 ---
 license: apache-2.0
-tags: [cybersecurity, security, vulnerability-analysis]
 ---
-# Mythoseek
-Mythoseek is a cybersecurity AI assistant created by squ11z1, built on the DeepSeek-V4 Pro architecture.

 ---
 license: apache-2.0
+language:
+- en
+tags:
+- transformers
+- safetensors
+- text-generation
+- cybersecurity
+- penetration-testing
+- vulnerability-research
+- osint
+- cwe
+- tool-use
+- reasoning
+- chain-of-thought
+- grpo
+- quantum-classical
+- kaon
+- ibm-quantum
+- aer
+- merlin-research
+- qwen3_5
+base_model: Qwen/Qwen3.5-9B-Base
+base_model_relation: finetune
+pipeline_tag: text-generation
 ---
+# Mythoseek-10B
+**squ11z1 · Merlin Research**
+> *Mythos* — after Claude Mythos, Anthropic's frontier cyber model.
+> *Seek* — after DeepSeek, the open-source movement.
+> **Mythoseek**: the open alternative.
+---
+## Overview
+Mythoseek-10B is a 10B parameter language model specialized for
+cybersecurity — vulnerability research, penetration testing, OSINT,
+and CWE-pattern reasoning. Fine-tuned from Qwen/Qwen3.5-9B-Base on
+confidential enterprise pentest reports and frontier model distillation
+traces, it brings closed-source cyber AI capability to the open
+community.
+Developed at **Merlin Research** (Stockholm, Sweden) as part of the
+**KAON** quantum-classical research program — a closed-loop framework
+connecting IBM Quantum (ibm_kingston, Heron r2) with edge LLM
+inference on Apple Silicon. OTOC scrambling measurements from real
+IBM QPU jobs informed AER (Adaptive Entropy Regularization)
+coefficient calibration during GRPO training.
+---
+## Training Pipeline
+| Stage | Method | Details |
+|---|---|---|
+| 1 | SFT Distillation | Frontier model trace distillation |
+| 2 | GRPO / RL | Verifiable rewards on cyber tasks |
+| 3 | Tool-use SFT | Agent-style tool calling |
+| 4 | CWE Grounding | CWE-pattern structured reasoning |
+---
+## CyberGym Results (arXiv:2506.02548)
+**CyberGym** — UC Berkeley's large-scale cybersecurity benchmark,
+1,507 real-world vulnerabilities from Google OSS-Fuzz across 188
+projects. No partial credit, no LLM judge — pass requires a valid
+PoC that crashes the pre-patch build.
+| Level | Scaffold | pass@4 |
+|---|---|---|
+| Level 0 | Full scaffolding | 62% |
+| Level 1 | Partial scaffolding | 34% |
+| Level 2 | Minimal scaffolding | 12% |
+| Level 3 | No scaffolding | 3% |
+> For reference: Claude Mythos Preview leads the public leaderboard
+> at 83.1% pass@1 (overall, closed model).
+> Mythoseek-10B is a 10B open-weight alternative.
+---
+## Intended Use
+- Vulnerability research and CVE analysis
+- Penetration testing assistance (OSINT, recon, XSS, SQLi)
+- CWE classification and pattern recognition
+- Security report generation
+- Red team reasoning support
+**Not intended for:** autonomous offensive operations,
+unauthorized access, or malicious use.
+---
+## KAON Connection
+This model is part of the **KAON** quantum-classical research program: