Instructions to use marekzel/mz-model-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use marekzel/mz-model-v1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="marekzel/mz-model-v1")# pip install -U transformers accelerate # Load model directly from transformers import MzModelV1 model = MzModelV1.from_pretrained("marekzel/mz-model-v1", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use marekzel/mz-model-v1 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "marekzel/mz-model-v1" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "marekzel/mz-model-v1", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/marekzel/mz-model-v1
- SGLang
How to use marekzel/mz-model-v1 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 "marekzel/mz-model-v1" \ --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": "marekzel/mz-model-v1", "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 "marekzel/mz-model-v1" \ --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": "marekzel/mz-model-v1", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use marekzel/mz-model-v1 with Docker Model Runner:
docker model run hf.co/marekzel/mz-model-v1
Download config.json from marekzel/mz-model-v1: direct link, hf CLI and curl.
- Browser
- Download file 272 Bytes
-
https://huggingface.co/marekzel/mz-model-v1/resolve/main/config.json
- Command line
-
hf download hf://marekzel/mz-model-v1/config.json
-
curl -L -o config.json https://huggingface.co/marekzel/mz-model-v1/resolve/main/config.json
272 Bytes
| { | |
| "architectures": [ | |
| "MzModelV1" | |
| ], | |
| "dtype": "float32", | |
| "hidden_size": 768, | |
| "max_position": 512, | |
| "model_type": "mz_model_v1", | |
| "num_heads": 12, | |
| "num_layers": 12, | |
| "tie_word_embeddings": true, | |
| "transformers_version": "5.17.0", | |
| "vocab_size": 32000 | |
| } | |