Instructions to use afoland/penchant-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use afoland/penchant-7B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="afoland/penchant-7B") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("afoland/penchant-7B") model = AutoModelForCausalLM.from_pretrained("afoland/penchant-7B", device_map="auto") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=40) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use afoland/penchant-7B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "afoland/penchant-7B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "afoland/penchant-7B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/afoland/penchant-7B
- SGLang
How to use afoland/penchant-7B 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 "afoland/penchant-7B" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "afoland/penchant-7B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'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 "afoland/penchant-7B" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "afoland/penchant-7B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use afoland/penchant-7B with Docker Model Runner:
docker model run hf.co/afoland/penchant-7B
| import sys | |
| import json | |
| import random | |
| from YOUR_API_CALLER_GOES_HERE import LLM_COMPLETION | |
| def get_response(title, poet): | |
| """ | |
| Creates poem-generation prompt from title and poet, and puts it into | |
| the expected penchant format | |
| """ | |
| penchant_prompt = f'Write an artistic poem. The title should be "{title}". Use vivid imagery and creative metaphors throughout your work. Draw inspiration from the works of {poet}. Pay close attention to the sounds that words make when read aloud, and use these sounds to create rhythm and musicality within your piece.' | |
| penchant_template = f"<|im_start|>system\nYou are Dolphin, a helpful AI assistant.<|im_end|>\n<|im_start|>user\n{penchant_prompt}<|im_end|>\n<|im_start|>assistant\n" | |
| poem = LLM_COMPLETION(penchant_template) | |
| return poem | |
| def process_files(titles_file, poets_file, output_file): | |
| try: | |
| # Read "titles" and "poets" from input files | |
| with open(titles_file, 'r') as f: | |
| titles_data = json.load(f) | |
| titles = titles_data.get("titles", []) | |
| with open(poets_file, 'r') as f: | |
| poets_data = json.load(f) | |
| poets = poets_data.get("poets", []) | |
| # Write responses to output JSONL file | |
| with open(output_file, 'w') as f: | |
| poems_to_write = 100 | |
| count = 0 | |
| while count < poems_to_write: | |
| title = random.choice(titles) | |
| poet = random.choice(poets) | |
| title = title.strip() | |
| poet = poet.strip() | |
| response = get_response(title, poet) | |
| output_data = {"poet": poet, "title": title, "poem": response} | |
| f.write(json.dumps(output_data) + "\n") | |
| count += 1 | |
| except FileNotFoundError as e: | |
| print(f"Error: {e.filename} not found.") | |
| except Exception as e: | |
| print(f"An error occurred: {e}") | |
| if __name__ == "__main__": | |
| if len(sys.argv) != 4: | |
| print("Usage: python script.py titles_file.json poets_file.json output_file.jsonl") | |
| else: | |
| titles_file = sys.argv[1] | |
| poets_file = sys.argv[2] | |
| output_file = sys.argv[3] | |
| process_files(titles_file, poets_file, output_file) | |