Text Generation
Transformers
Safetensors
French
English
Chinese
deepseek_v4
cortex
code-generation
web-development
software-engineering
Mixture of Experts
8-bit precision
fp8
Instructions to use Frankenstein-Labs/cortex.6.sol with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
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
Download datasets/registry.json from Frankenstein-Labs/cortex.6.sol: direct link, hf CLI and curl.
- Browser
- Download file 3.8 kB
-
https://huggingface.co/Frankenstein-Labs/cortex.6.sol/resolve/main/datasets/registry.json
- Command line
-
hf download hf://Frankenstein-Labs/cortex.6.sol/datasets/registry.json
-
curl -L -o registry.json https://huggingface.co/Frankenstein-Labs/cortex.6.sol/resolve/main/datasets/registry.json
3.8 kB
| { | |
| "_comment": [ | |
| "Declared sources for CORTEX training data.", | |
| "Every dataset must state its origin and license. training/train.py refuses to run on", | |
| "a dataset that is not declared here or whose license is unknown, absent or proprietary.", | |
| "Licenses below were read from the Hugging Face Hub API, not from memory." | |
| ], | |
| "schema_version": 1, | |
| "datasets": [ | |
| { | |
| "id": "cortex-code-sft", | |
| "source": "sahil2801/CodeAlpaca-20k", | |
| "config": "default", | |
| "split": "train", | |
| "origin": "Hugging Face Hub dataset repository sahil2801/CodeAlpaca-20k", | |
| "license": "cc-by-4.0", | |
| "license_url": "https://huggingface.co/datasets/sahil2801/CodeAlpaca-20k", | |
| "redistribution": "yes", | |
| "attribution": "CodeAlpaca-20k, distributed under CC BY 4.0. Attribution required: cite the dataset repository above when redistributing.", | |
| "record_type": "code-sft", | |
| "fields": { | |
| "prompt": "instruction", | |
| "completion": "output", | |
| "instruction_field": "instruction", | |
| "input_field": "input" | |
| }, | |
| "id_field": null, | |
| "path": "datasets/cortex-code-sft.jsonl", | |
| "note": "Instruction/response pairs for code generation. CC BY 4.0 permits redistribution and commercial use with attribution." | |
| }, | |
| { | |
| "id": "cortex-code-tests", | |
| "source": "google-research-datasets/mbpp", | |
| "config": "full", | |
| "split": "test", | |
| "origin": "Hugging Face Hub dataset repository google-research-datasets/mbpp", | |
| "license": "cc-by-4.0", | |
| "license_url": "https://huggingface.co/datasets/google-research-datasets/mbpp", | |
| "redistribution": "yes", | |
| "attribution": "MBPP (Mostly Basic Python Problems), Google Research, distributed under CC BY 4.0.", | |
| "record_type": "code-sft", | |
| "fields": { | |
| "prompt": "text", | |
| "completion": "code" | |
| }, | |
| "id_field": "task_id", | |
| "path": "datasets/cortex-code-tests.jsonl", | |
| "note": "Python problem statements with reference solutions. Suitable for evaluation and instruction tuning." | |
| }, | |
| { | |
| "id": "cortex-code-eval", | |
| "source": "openai/openai_humaneval", | |
| "config": "openai_humaneval", | |
| "split": "test", | |
| "origin": "Hugging Face Hub dataset repository openai/openai_humaneval", | |
| "license": "mit", | |
| "license_url": "https://huggingface.co/datasets/openai/openai_humaneval", | |
| "redistribution": "yes", | |
| "attribution": "HumanEval, OpenAI, distributed under the MIT license.", | |
| "record_type": "code-sft", | |
| "fields": { | |
| "prompt": "prompt", | |
| "completion": "canonical_solution" | |
| }, | |
| "id_field": "task_id", | |
| "path": "datasets/cortex-code-eval.jsonl", | |
| "note": "Held out for evaluation only. Must not be trained on: doing so would invalidate the evaluation." | |
| } | |
| ], | |
| "rejected": [ | |
| { | |
| "source": "bigcode/the-stack-dedup", | |
| "license": "other", | |
| "reason": "License field is 'other' with gated access; the governing terms are not verifiable from the Hub metadata alone." | |
| }, | |
| { | |
| "source": "bigcode/starcoderdata", | |
| "license": "other", | |
| "reason": "License field is 'other' and access is gated; per-file source licenses are not declared at dataset level." | |
| }, | |
| { | |
| "source": "codeparrot/codeparrot-clean", | |
| "license": null, | |
| "reason": "No license declared on the Hub. Cannot be redistributed or used without an explicit grant." | |
| }, | |
| { | |
| "source": "codeparrot/github-code", | |
| "license": "other", | |
| "reason": "License field is 'other'; terms are not verifiable from Hub metadata alone." | |
| }, | |
| { | |
| "source": "iamtarun/python_code_instructions_18k_alpaca", | |
| "license": null, | |
| "reason": "No license declared on the Hub." | |
| } | |
| ] | |
| } | |