Instructions to use nvidia/Nemotron-Labs-Diffusion-3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nvidia/Nemotron-Labs-Diffusion-3B with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="nvidia/Nemotron-Labs-Diffusion-3B", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("nvidia/Nemotron-Labs-Diffusion-3B", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use nvidia/Nemotron-Labs-Diffusion-3B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nvidia/Nemotron-Labs-Diffusion-3B"
# 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/Nemotron-Labs-Diffusion-3B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nvidia/Nemotron-Labs-Diffusion-3B

SGLang

How to use nvidia/Nemotron-Labs-Diffusion-3B 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 "nvidia/Nemotron-Labs-Diffusion-3B" \
    --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/Nemotron-Labs-Diffusion-3B",
		"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 "nvidia/Nemotron-Labs-Diffusion-3B" \
        --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/Nemotron-Labs-Diffusion-3B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use nvidia/Nemotron-Labs-Diffusion-3B with Docker Model Runner:
```
docker model run hf.co/nvidia/Nemotron-Labs-Diffusion-3B
```

YongganFu commited on Mar 12

Commit

5cddf22

verified ·

1 Parent(s): b9d4dfe

Update README.md

Browse files

Files changed (1) hide show

README.md +36 -3

README.md CHANGED Viewed

@@ -16,7 +16,7 @@ Docker path: `/lustre/fsw/portfolios/nvr/users/yongganf/docker/megatron_py25_dll
 srun -A {account} --partition interactive --time 4:00:00 --gpus 8 --container-image /lustre/fsw/portfolios/nvr/users/yongganf/docker/megatron_py25_dllm_ministral.sqsh --container-mounts=$HOME:/home,/lustre:/lustre  --pty bash
 ```
-## Chat with Our Model
 ```
@@ -36,9 +36,42 @@ history.append({"role": "user", "content": user_input})
 prompt = tokenizer.apply_chat_template(history, tokenize=False, add_generation_prompt=True)
 prompt_ids = tokenizer(prompt, return_tensors='pt').input_ids.to(device='cuda')
-out_ids, nfe = model.generate(prompt_ids, max_new_tokens=128, steps=128, block_length=32, shift_logits=False, causal_context=True, threshold=0.9, eos_token_id=tokenizer.eos_token_id)
 tokenized_out = tokenizer.batch_decode(out_ids[:, prompt_ids.shape[1]:], skip_special_tokens=True)[0]
 print(f"Model: {tokenized_out}")
 print(f"[Num Function Eval (NFE)={nfe}]")
-```

 srun -A {account} --partition interactive --time 4:00:00 --gpus 8 --container-image /lustre/fsw/portfolios/nvr/users/yongganf/docker/megatron_py25_dllm_ministral.sqsh --container-mounts=$HOME:/home,/lustre:/lustre  --pty bash
 ```
+## Chat with Our Model in dLM Mode
 ```
 prompt = tokenizer.apply_chat_template(history, tokenize=False, add_generation_prompt=True)
 prompt_ids = tokenizer(prompt, return_tensors='pt').input_ids.to(device='cuda')
+out_ids, nfe = model.generate(prompt_ids, max_new_tokens=512, steps=512, block_length=32, shift_logits=False, causal_context=True, threshold=0.9, eos_token_id=tokenizer.eos_token_id)
 tokenized_out = tokenizer.batch_decode(out_ids[:, prompt_ids.shape[1]:], skip_special_tokens=True)[0]
 print(f"Model: {tokenized_out}")
 print(f"[Num Function Eval (NFE)={nfe}]")
+```
+## Chat with Our Model in Self-Speculation Mode
+```
+from transformers import AutoModel, AutoTokenizer, AutoConfig
+import torch
+repo_name = "nvidia/Nemotron-Diffusion-Exp-Ministral-3B-Instruct"
+tokenizer = AutoTokenizer.from_pretrained(repo_name, trust_remote_code=True)
+config = AutoConfig.from_pretrained(repo_name, trust_remote_code=True)
+config.enable_self_spec = True
+model = AutoModel.from_pretrained(repo_name, config=config, trust_remote_code=True).cuda().to(torch.bfloat16)
+history = []
+user_input = input("User: ").strip()
+history.append({"role": "user", "content": user_input})
+prompt = tokenizer.apply_chat_template(history, tokenize=False, add_generation_prompt=True)
+inputs = tokenizer(prompt, return_tensors="pt")
+inputs = inputs.to("cuda")
+out_ids, nfe = model.self_spec_generate(inputs.input_ids, max_new_tokens=512, steps=512, block_length=32, ar_mix_weight=0.5, eos_token_id=tokenizer.eos_token_id)
+tokenized_out = tokenizer.batch_decode(out_ids[:, inputs.input_ids.shape[1]:], skip_special_tokens=True)[0]
+print(f"Model: {tokenized_out}")
+print(f"[Num Function Eval (NFE)={nfe}]")
+```