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
| #!/usr/bin/env python3 | |
| """ | |
| Push Zenith-7B model to Hugging Face Hub. | |
| Usage: | |
| python push_to_hf.py --repo_id Matrix-Corp/Zenith-7b-V1 --token YOUR_TOKEN | |
| """ | |
| import argparse | |
| import os | |
| import sys | |
| from pathlib import Path | |
| from huggingface_hub import HfApi, login, create_repo, whoami | |
| from huggingface_hub.utils import RepositoryNotFoundError, HfHubHTTPError | |
| def push_model(repo_id: str, token: str = None, folder_path: str = ".", private: bool = False): | |
| """Push model files to Hugging Face Hub with robust error handling.""" | |
| folder_path = Path(folder_path).resolve() | |
| if not folder_path.exists(): | |
| raise ValueError(f"Folder not found: {folder_path}") | |
| # Check required files | |
| required_files = [ | |
| "modeling_zenith.py", | |
| "hf_model_card.md", | |
| "README.md", | |
| "requirements.txt", | |
| "train.py", | |
| "inference.py", | |
| "test_model.py", | |
| "finetune_qwen.py", | |
| "Modelfile" | |
| ] | |
| missing = [f for f in required_files if not (folder_path / f).exists()] | |
| if missing: | |
| print(f"⚠️ Warning: Missing files: {missing}") | |
| response = input("Continue anyway? (y/N): ") | |
| if response.lower() != 'y': | |
| return | |
| # Authenticate | |
| try: | |
| if token: | |
| login(token=token) | |
| print("✓ Logged in with provided token") | |
| else: | |
| # Check if already logged in | |
| try: | |
| user = whoami() | |
| print(f"✓ Already logged in as: {user['name']}") | |
| except: | |
| print("Please login to Hugging Face:") | |
| login() | |
| except Exception as e: | |
| print(f"❌ Authentication failed: {e}") | |
| print("\nTo get a token:") | |
| print("1. Go to https://huggingface.co/settings/tokens") | |
| print("2. Create a new token with 'write' permissions") | |
| print("3. Run: python push_to_hf.py --token YOUR_TOKEN") | |
| return | |
| # Create API client | |
| api = HfApi() | |
| # Check if repo exists, create if not | |
| try: | |
| repo_info = api.repo_info(repo_id=repo_id, repo_type="model") | |
| print(f"✓ Repository exists: {repo_id}") | |
| except RepositoryNotFoundError: | |
| print(f"📝 Repository not found. Creating: {repo_id}") | |
| try: | |
| create_repo( | |
| repo_id=repo_id, | |
| token=token, | |
| repo_type="model", | |
| private=private, | |
| exist_ok=True | |
| ) | |
| print(f"✓ Repository created") | |
| except Exception as e: | |
| print(f"❌ Failed to create repository: {e}") | |
| return | |
| except Exception as e: | |
| print(f"⚠️ Warning: Could not check repository: {e}") | |
| # Upload | |
| print(f"\n📤 Uploading {folder_path} to {repo_id}...") | |
| print("This may take a while depending on file sizes...\n") | |
| try: | |
| api.upload_folder( | |
| folder_path=str(folder_path), | |
| repo_id=repo_id, | |
| repo_type="model", | |
| commit_message=f"Upload Zenith-7B model" | |
| ) | |
| print(f"\n✅ Successfully uploaded to https://huggingface.co/{repo_id}") | |
| print("\nNext steps:") | |
| print("1. Visit your model page") | |
| print("2. Add a model card if needed") | |
| print("3. Test: from transformers import AutoModel; AutoModel.from_pretrained('your-repo-id')") | |
| except HfHubHTTPError as e: | |
| if e.response.status_code == 401: | |
| print(f"\n❌ Unauthorized: Invalid token or no write access") | |
| print(" Make sure you:") | |
| print(" - Have a valid token with 'write' permissions") | |
| print(" - Own the organization/repository or have collaborator rights") | |
| elif e.response.status_code == 403: | |
| print(f"\n❌ Forbidden: You don't have permission to push to this repository") | |
| print(" Make sure you're a member of the organization with write access") | |
| elif e.response.status_code == 404: | |
| print(f"\n❌ Repository not found: {repo_id}") | |
| print(" Check the repository ID is correct") | |
| else: | |
| print(f"\n❌ HTTP Error {e.response.status_code}: {e}") | |
| except Exception as e: | |
| print(f"\n❌ Upload failed: {e}") | |
| print("\nTroubleshooting:") | |
| print("1. Check your internet connection") | |
| print("2. Verify you have enough disk space") | |
| print("3. Try logging in again: huggingface-cli login") | |
| print("4. Check Hugging Face status: https://status.huggingface.co") | |
| def main(): | |
| parser = argparse.ArgumentParser(description="Push Zenith-7B to Hugging Face") | |
| parser.add_argument( | |
| "--repo_id", | |
| type=str, | |
| default="Matrix-Corp/Zenith-7b-V1", | |
| help="Hugging Face repository ID (username/model-name)" | |
| ) | |
| parser.add_argument( | |
| "--token", | |
| type=str, | |
| help="Hugging Face access token (optional if already logged in)" | |
| ) | |
| parser.add_argument( | |
| "--folder", | |
| type=str, | |
| default=".", | |
| help="Folder containing model files (default: current directory)" | |
| ) | |
| parser.add_argument( | |
| "--private", | |
| action="store_true", | |
| help="Create repository as private (default: public)" | |
| ) | |
| args = parser.parse_args() | |
| push_model(args.repo_id, args.token, args.folder, args.private) | |
| if __name__ == "__main__": | |
| main() | |