How to use echo840/Monkey with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="echo840/Monkey", trust_remote_code=True)
# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("echo840/Monkey", trust_remote_code=True, dtype="auto")
How to use echo840/Monkey with vLLM:
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "echo840/Monkey" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "echo840/Monkey", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'
docker model run hf.co/echo840/Monkey
How to use echo840/Monkey with SGLang:
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "echo840/Monkey" \ --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": "echo840/Monkey", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'
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 "echo840/Monkey" \ --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": "echo840/Monkey", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'
How to use echo840/Monkey with Docker Model Runner:
I am using the demo.py but the model goes OOM even after having 96Gb of GPU memory. Looks like it is only using single gpu and not distributing the model into multiple GPUs.
· Sign up or log in to comment
