Instructions to use Frankenstein-Labs/cortex.6.sol with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Frankenstein-Labs/cortex.6.sol with Transformers:

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

pipe = pipeline("text-generation", model="Frankenstein-Labs/cortex.6.sol")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Frankenstein-Labs/cortex.6.sol")
model = AutoModelForCausalLM.from_pretrained("Frankenstein-Labs/cortex.6.sol", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Frankenstein-Labs/cortex.6.sol with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Frankenstein-Labs/cortex.6.sol"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Frankenstein-Labs/cortex.6.sol",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Frankenstein-Labs/cortex.6.sol

SGLang

How to use Frankenstein-Labs/cortex.6.sol 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 "Frankenstein-Labs/cortex.6.sol" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Frankenstein-Labs/cortex.6.sol",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "Frankenstein-Labs/cortex.6.sol" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Frankenstein-Labs/cortex.6.sol",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Frankenstein-Labs/cortex.6.sol with Docker Model Runner:
```
docker model run hf.co/Frankenstein-Labs/cortex.6.sol
```

cortex.6.sol / tests /test_config.py

asdfasdfqrqwer

feat(cortex-ai): agent engine, tool registry, OpenAI-compatible API, fine-tuning pipeline

c63bc31 about 1 month ago

Raw History Blame Contribute Delete

2.28 kB

"""Tests for configuration loading and validation."""

import json

import pytest

from cortex_ai.config import CortexConfig, EngineConfig, ServerConfig, DEFAULT_MODEL_ID


def test_defaults():
    cfg = CortexConfig()
    assert cfg.model_id == DEFAULT_MODEL_ID
    assert cfg.engine.thinking_mode == "thinking"
    assert cfg.engine.reasoning_effort == "high"
    assert cfg.server.requires_auth is False


def test_invalid_thinking_mode_is_rejected():
    with pytest.raises(ValueError, match="thinking_mode"):
        EngineConfig(thinking_mode="turbo")


def test_invalid_reasoning_effort_is_rejected():
    with pytest.raises(ValueError, match="reasoning_effort"):
        EngineConfig(reasoning_effort="extreme")


def test_invalid_max_tool_rounds_is_rejected():
    with pytest.raises(ValueError, match="max_tool_rounds"):
        EngineConfig(max_tool_rounds=0)


def test_round_trip_through_dict():
    cfg = CortexConfig(
        model_id="exemple/modele",
        engine=EngineConfig(thinking_mode="chat", max_tool_rounds=3),
        enabled_tools=["calculate"],
    )
    restored = CortexConfig.from_dict(cfg.to_dict())
    assert restored.model_id == "exemple/modele"
    assert restored.engine.thinking_mode == "chat"
    assert restored.engine.max_tool_rounds == 3
    assert restored.enabled_tools == ["calculate"]


def test_save_and_load_a_file(tmp_path):
    path = tmp_path / "cortex.json"
    cfg = CortexConfig(model_id="exemple/enregistre")
    cfg.save(path)
    assert json.loads(path.read_text())["model_id"] == "exemple/enregistre"
    assert CortexConfig.load(path).model_id == "exemple/enregistre"


def test_env_overrides(monkeypatch):
    monkeypatch.setenv("CORTEX_MODEL_ID", "exemple/depuis-env")
    monkeypatch.setenv("CORTEX_PORT", "9001")
    monkeypatch.setenv("CORTEX_THINKING_MODE", "chat")
    monkeypatch.setenv("CORTEX_TOOLS", "calculate, text_stats")
    cfg = CortexConfig.from_env()
    assert cfg.model_id == "exemple/depuis-env"
    assert cfg.server.port == 9001
    assert cfg.engine.thinking_mode == "chat"
    assert cfg.enabled_tools == ["calculate", "text_stats"]


def test_api_key_makes_auth_required():
    assert ServerConfig(api_key="abc").requires_auth is True
    assert ServerConfig(api_key="").requires_auth is False

	"""Tests for configuration loading and validation."""

	import json

	import pytest

	from cortex_ai.config import CortexConfig, EngineConfig, ServerConfig, DEFAULT_MODEL_ID


	def test_defaults():
	cfg = CortexConfig()
	assert cfg.model_id == DEFAULT_MODEL_ID
	assert cfg.engine.thinking_mode == "thinking"
	assert cfg.engine.reasoning_effort == "high"
	assert cfg.server.requires_auth is False


	def test_invalid_thinking_mode_is_rejected():
	with pytest.raises(ValueError, match="thinking_mode"):
	EngineConfig(thinking_mode="turbo")


	def test_invalid_reasoning_effort_is_rejected():
	with pytest.raises(ValueError, match="reasoning_effort"):
	EngineConfig(reasoning_effort="extreme")


	def test_invalid_max_tool_rounds_is_rejected():
	with pytest.raises(ValueError, match="max_tool_rounds"):
	EngineConfig(max_tool_rounds=0)


	def test_round_trip_through_dict():
	cfg = CortexConfig(
	model_id="exemple/modele",
	engine=EngineConfig(thinking_mode="chat", max_tool_rounds=3),
	enabled_tools=["calculate"],
	)
	restored = CortexConfig.from_dict(cfg.to_dict())
	assert restored.model_id == "exemple/modele"
	assert restored.engine.thinking_mode == "chat"
	assert restored.engine.max_tool_rounds == 3
	assert restored.enabled_tools == ["calculate"]


	def test_save_and_load_a_file(tmp_path):
	path = tmp_path / "cortex.json"
	cfg = CortexConfig(model_id="exemple/enregistre")
	cfg.save(path)
	assert json.loads(path.read_text())["model_id"] == "exemple/enregistre"
	assert CortexConfig.load(path).model_id == "exemple/enregistre"


	def test_env_overrides(monkeypatch):
	monkeypatch.setenv("CORTEX_MODEL_ID", "exemple/depuis-env")
	monkeypatch.setenv("CORTEX_PORT", "9001")
	monkeypatch.setenv("CORTEX_THINKING_MODE", "chat")
	monkeypatch.setenv("CORTEX_TOOLS", "calculate, text_stats")
	cfg = CortexConfig.from_env()
	assert cfg.model_id == "exemple/depuis-env"
	assert cfg.server.port == 9001
	assert cfg.engine.thinking_mode == "chat"
	assert cfg.enabled_tools == ["calculate", "text_stats"]


	def test_api_key_makes_auth_required():
	assert ServerConfig(api_key="abc").requires_auth is True
	assert ServerConfig(api_key="").requires_auth is False