Text Generation
Transformers
PyTorch
Safetensors
English
llama
pretrained
mistral-common
text-generation-inference
Instructions to use chatpbc1/chatpbc-v33 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use chatpbc1/chatpbc-v33 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="chatpbc1/chatpbc-v33")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("chatpbc1/chatpbc-v33") model = AutoModelForCausalLM.from_pretrained("chatpbc1/chatpbc-v33", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use chatpbc1/chatpbc-v33 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Install mistral-common: pip install --upgrade mistral-common # Start the vLLM server: vllm serve "chatpbc1/chatpbc-v33" --tokenizer_mode mistral --config_format mistral --load_format mistral --tool-call-parser mistral --enable-auto-tool-choice # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "chatpbc1/chatpbc-v33", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/chatpbc1/chatpbc-v33
- SGLang
How to use chatpbc1/chatpbc-v33 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 "chatpbc1/chatpbc-v33" \ --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": "chatpbc1/chatpbc-v33", "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 "chatpbc1/chatpbc-v33" \ --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": "chatpbc1/chatpbc-v33", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use chatpbc1/chatpbc-v33 with Docker Model Runner:
docker model run hf.co/chatpbc1/chatpbc-v33
| import os | |
| def process_file(file_path): | |
| """ | |
| Processes uploaded business documents to extract text for analysis. | |
| """ | |
| _, extension = os.path.splitext(file_path) | |
| extension = extension.lower() | |
| try: | |
| if extension == '.txt': | |
| with open(file_path, 'r', encoding='utf-8') as f: | |
| return f.read() | |
| elif extension == '.md': | |
| with open(file_path, 'r', encoding='utf-8') as f: | |
| return f.read() | |
| else: | |
| return f"Unsupported file type: {extension}. Currently only .txt and .md are supported for direct extraction." | |
| except Exception as e: | |
| return f"Error processing file: {str(e)}" | |
| if __name__ == "__main__": | |
| # Test with a dummy file | |
| test_file = "test_doc.txt" | |
| with open(test_file, "w") as f: | |
| f.write("This is a sample business document for ChatPBC analysis.") | |
| content = process_file(test_file) | |
| print(f"Processed file content: {content}") | |
| os.remove(test_file) | |