Text Generation
Transformers
Safetensors
English
mistral
Eval Results (legacy)
text-generation-inference
Instructions to use jan-hq/supermario-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use jan-hq/supermario-v2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="jan-hq/supermario-v2")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("jan-hq/supermario-v2") model = AutoModelForCausalLM.from_pretrained("jan-hq/supermario-v2") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use jan-hq/supermario-v2 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "jan-hq/supermario-v2" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "jan-hq/supermario-v2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/jan-hq/supermario-v2
- SGLang
How to use jan-hq/supermario-v2 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 "jan-hq/supermario-v2" \ --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": "jan-hq/supermario-v2", "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 "jan-hq/supermario-v2" \ --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": "jan-hq/supermario-v2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use jan-hq/supermario-v2 with Docker Model Runner:
docker model run hf.co/jan-hq/supermario-v2
Why use Marcoroni?
#2
by debackerl - opened
Hello,
Why the interest in using Marcoroni? It's also based on MetaMath-Cybertron-Starling which you use, but they added "just" 32k prompts, but those prompts were never shared, and it's not clear if they were not contaminated by benchmark data.
Thank you for the great work :-)
Laurent
Actually, these are experimental models, so we just try various types of merging models.
Glad to hear more feedback from you.