How to use blue-blues/93 with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("ServiceNow-AI/Apriel-1.5-15b-Thinker") model = PeftModel.from_pretrained(base_model, "blue-blues/93")
How to use blue-blues/93 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="blue-blues/93") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("blue-blues/93", dtype="auto")
How to use blue-blues/93 with vLLM:
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "blue-blues/93" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "blue-blues/93", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'
docker model run hf.co/blue-blues/93
How to use blue-blues/93 with SGLang:
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "blue-blues/93" \ --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": "blue-blues/93", "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 "blue-blues/93" \ --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": "blue-blues/93", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'
How to use blue-blues/93 with Docker Model Runner: