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

Libraries

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

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

pipe = pipeline("text-generation", model="nvidia/Nemotron-Labs-Diffusion-3B-Base", 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-Base", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

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

Use Docker

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

SGLang

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

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

YongganFu commited on about 6 hours ago

Commit

804d4b4

verified ·

1 Parent(s): 39c8fdc

Sync tokenizer to the instruct variant (vocab + special tokens for chat template)

Browse files

Files changed (3) hide show

special_tokens_map.json +1 -1
tokenizer.json +2 -2
tokenizer_config.json +17 -17

special_tokens_map.json CHANGED Viewed

@@ -7,7 +7,7 @@
     "single_word": false
   },
   "eos_token": {
-    "content": "</s>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

     "single_word": false
   },
   "eos_token": {
+    "content": "<|im_end|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer.json CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3277c00fe5fb3963b3cb7c07b7f183722d2af4d775a4aea7cfb3684d7cccbc2f
-size 17078330

 version https://git-lfs.github.com/spec/v1
+oid sha256:623c34567aebb18582765289fbe23d901c62704d6518d71866e0e58db892b5b7
+size 17077484

tokenizer_config.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-  "add_bos_token": true,
   "add_eos_token": false,
   "add_prefix_space": false,
   "added_tokens_decoder": {
@@ -84,7 +84,7 @@
       "special": true
     },
     "10": {
-      "content": "<SPECIAL_10>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -92,7 +92,7 @@
       "special": true
     },
     "11": {
-      "content": "<SPECIAL_11>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -100,52 +100,52 @@
       "special": true
     },
     "12": {
-      "content": "<SPECIAL_12>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": true
     },
     "13": {
-      "content": "<SPECIAL_13>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": true
     },
     "14": {
-      "content": "<SPECIAL_14>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": true
     },
     "15": {
-      "content": "<SPECIAL_15>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": true
     },
     "16": {
-      "content": "<SPECIAL_16>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": true
     },
     "17": {
-      "content": "<SPECIAL_17>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": true
     },
     "18": {
       "content": "<SPECIAL_18>",
@@ -8006,13 +8006,13 @@
   },
   "bos_token": "<s>",
   "clean_up_tokenization_spaces": false,
-  "eos_token": "</s>",
   "extra_special_tokens": {},
   "model_input_names": [
     "input_ids",
     "attention_mask"
   ],
-  "model_max_length": 8192,
   "tokenizer_class": "PreTrainedTokenizerFast",
   "unk_token": "<unk>"
 }

 {
+  "add_bos_token": false,
   "add_eos_token": false,
   "add_prefix_space": false,
   "added_tokens_decoder": {
       "special": true
     },
     "10": {
+      "content": "<|im_start|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "special": true
     },
     "11": {
+      "content": "<|im_end|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "special": true
     },
     "12": {
+      "content": "<think>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
+      "special": false
     },
     "13": {
+      "content": "</think>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
+      "special": false
     },
     "14": {
+      "content": "<tool_call>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
+      "special": false
     },
     "15": {
+      "content": "</tool_call>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
+      "special": false
     },
     "16": {
+      "content": "<tool_response>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
+      "special": false
     },
     "17": {
+      "content": "</tool_response>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
+      "special": false
     },
     "18": {
       "content": "<SPECIAL_18>",
   },
   "bos_token": "<s>",
   "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
   "extra_special_tokens": {},
   "model_input_names": [
     "input_ids",
     "attention_mask"
   ],
+  "model_max_length": 262144,
   "tokenizer_class": "PreTrainedTokenizerFast",
   "unk_token": "<unk>"
 }