How to use nvidia/Efficient-DLM-8B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="nvidia/Efficient-DLM-8B", trust_remote_code=True) messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)
# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("nvidia/Efficient-DLM-8B", trust_remote_code=True) model = AutoModel.from_pretrained("nvidia/Efficient-DLM-8B", trust_remote_code=True) 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]:]))
How to use nvidia/Efficient-DLM-8B with vLLM:
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "nvidia/Efficient-DLM-8B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "nvidia/Efficient-DLM-8B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'
docker model run hf.co/nvidia/Efficient-DLM-8B
How to use nvidia/Efficient-DLM-8B with SGLang:
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "nvidia/Efficient-DLM-8B" \ --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": "nvidia/Efficient-DLM-8B", "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 "nvidia/Efficient-DLM-8B" \ --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": "nvidia/Efficient-DLM-8B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'
How to use nvidia/Efficient-DLM-8B with Docker Model Runner:
Very cool to see this done on smaller models; however, do you have any idea if this could be extended to larger models and what the training costs would be? Also, does this only work for dense models, or can this be applied to MOE?
· Sign up or log in to comment
