How to use LucidityAI/Synth-1-preview with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="LucidityAI/Synth-1-preview") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("LucidityAI/Synth-1-preview") model = AutoModelForCausalLM.from_pretrained("LucidityAI/Synth-1-preview", 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=256) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))
How to use LucidityAI/Synth-1-preview with vLLM:
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "LucidityAI/Synth-1-preview" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "LucidityAI/Synth-1-preview", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'
docker model run hf.co/LucidityAI/Synth-1-preview
How to use LucidityAI/Synth-1-preview with SGLang:
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "LucidityAI/Synth-1-preview" \ --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": "LucidityAI/Synth-1-preview", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'
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 "LucidityAI/Synth-1-preview" \ --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": "LucidityAI/Synth-1-preview", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'
How to use LucidityAI/Synth-1-preview with Docker Model Runner:
# Install vLLM from pip: pip install vllm
# Start the vLLM server: vllm serve "LucidityAI/Synth-1-preview"
# Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "LucidityAI/Synth-1-preview", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'
Synth-1 is a LLM with the sole purpose of generating high quality creative text. Based on Qwen 2.5 3b.
Synth is currently in Beta and changes may occur often.
Install from pip and serve model
# Install vLLM from pip: pip install vllm# Start the vLLM server: vllm serve "LucidityAI/Synth-1-preview"# Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "LucidityAI/Synth-1-preview", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'