Text Generation
Transformers
English
zenith
tenstorrent
code
reasoning
Mixture of Experts
ring-attention
eq-adapter
matrix-corp
Instructions to use Matrix-Corp/Zenith-7b-V1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Matrix-Corp/Zenith-7b-V1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Matrix-Corp/Zenith-7b-V1")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Matrix-Corp/Zenith-7b-V1", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Matrix-Corp/Zenith-7b-V1 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Matrix-Corp/Zenith-7b-V1" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Matrix-Corp/Zenith-7b-V1", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Matrix-Corp/Zenith-7b-V1
- SGLang
How to use Matrix-Corp/Zenith-7b-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 "Matrix-Corp/Zenith-7b-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": "Matrix-Corp/Zenith-7b-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 "Matrix-Corp/Zenith-7b-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": "Matrix-Corp/Zenith-7b-V1", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Matrix-Corp/Zenith-7b-V1 with Docker Model Runner:
docker model run hf.co/Matrix-Corp/Zenith-7b-V1
| # Zenith-7B Dependencies | |
| # Install with: pip install -r requirements.txt | |
| # Core ML Framework | |
| torch>=2.0.0 | |
| torchvision | |
| torchaudio | |
| # Hugging Face Ecosystem | |
| transformers>=4.35.0 | |
| datasets>=2.14.0 | |
| accelerate>=0.24.0 | |
| huggingface-hub>=0.17.0 | |
| sentencepiece | |
| tokenizers>=0.14.0 | |
| # LoRA and Quantization | |
| peft>=0.6.0 | |
| bitsandbytes>=0.41.0 | |
| scipy | |
| # Data Processing | |
| numpy>=1.24.0 | |
| pandas>=2.0.0 | |
| pyarrow>=12.0.0 | |
| dask[dataframe]>=2023.1.0 | |
| # Evaluation | |
| evaluate>=0.4.0 | |
| scikit-learn>=1.3.0 | |
| rouge-score>=0.1.2 | |
| bert-score>=0.3.13 | |
| sacrebleu>=2.3.1 | |
| # Logging and Monitoring | |
| tensorboard>=2.14.0 | |
| wandb>=0.15.0 # Optional | |
| # Utilities | |
| tqdm>=4.65.0 | |
| pyyaml>=6.0 | |
| jsonlines>=4.0.0 | |
| hydra-core>=1.3.0 | |
| omegaconf>=2.3.0 | |
| # Development and Testing | |
| pytest>=7.4.0 | |
| pytest-cov>=4.1.0 | |
| black>=23.0.0 | |
| isort>=5.12.0 | |
| flake8>=6.0.0 | |
| mypy>=1.3.0 | |
| # Optional: Flash Attention (for faster training on Ampere+ GPUs) | |
| # flash-attn --no-build-isolation | |
| # Optional: vLLM for high-throughput inference | |
| # vllm>=0.2.0 |