Instructions to use nvidia/Nemotron-Labs-Diffusion-8B-Base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nvidia/Nemotron-Labs-Diffusion-8B-Base with Transformers:

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

pipe = pipeline("text-generation", model="nvidia/Nemotron-Labs-Diffusion-8B-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-8B-Base", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use nvidia/Nemotron-Labs-Diffusion-8B-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-8B-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-8B-Base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nvidia/Nemotron-Labs-Diffusion-8B-Base

SGLang

How to use nvidia/Nemotron-Labs-Diffusion-8B-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-8B-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-8B-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-8B-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-8B-Base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use nvidia/Nemotron-Labs-Diffusion-8B-Base with Docker Model Runner:
```
docker model run hf.co/nvidia/Nemotron-Labs-Diffusion-8B-Base
```

YongganFu commited on 18 days ago

Commit

85eb9d3

verified ·

1 Parent(s): f318bfe

Upload tokenizer

Browse files

Files changed (2) hide show

chat_template.jinja +7 -89
tokenizer_config.json +7 -6

chat_template.jinja CHANGED Viewed

@@ -1,89 +1,7 @@
-{%- if tools %}
-    {{- '<s>system\n' }}
-    {%- if messages[0].role == 'system' %}
-        {{- messages[0].content + '\n\n' }}
-    {%- endif %}
-    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within [AVAILABLE_TOOLS][/AVAILABLE_TOOLS] XML tags:\n[AVAILABLE_TOOLS]" }}
-    {%- for tool in tools %}
-        {{- "\n" }}
-        {{- tool | tojson }}
-    {%- endfor %}
-    {{- "\n[/AVAILABLE_TOOLS]\n\nFor each function call, return a json object with function name and arguments within [TOOL_CALLS][SPECIAL_10] XML tags:\n[TOOL_CALLS]\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n[SPECIAL_10]</s>\n" }}
-{%- else %}
-    {%- if messages[0].role == 'system' %}
-        {{- '<s>system\n' + messages[0].content + '</s>\n' }}
-    {%- endif %}
-{%- endif %}
-{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
-{%- for message in messages[::-1] %}
-    {%- set index = (messages|length - 1) - loop.index0 %}
-    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('[TOOL_RESULTS]') and message.content.endswith('[/TOOL_RESULTS]')) %}
-        {%- set ns.multi_step_tool = false %}
-        {%- set ns.last_query_index = index %}
-    {%- endif %}
-{%- endfor %}
-{%- for message in messages %}
-    {%- if message.content is string %}
-        {%- set content = message.content %}
-    {%- else %}
-        {%- set content = '' %}
-    {%- endif %}
-    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
-        {{- '<s>' + message.role + '\n' + content + '</s>' + '\n' }}
-    {%- elif message.role == "assistant" %}
-        {%- set reasoning_content = '' %}
-        {%- if message.reasoning_content is string %}
-            {%- set reasoning_content = message.reasoning_content %}
-        {%- else %}
-            {%- if '<SPECIAL_12>' in content %}
-                {%- set reasoning_content = content.split('<SPECIAL_12>')[0].rstrip('\n').split('<SPECIAL_11>')[-1].lstrip('\n') %}
-                {%- set content = content.split('<SPECIAL_12>')[-1].lstrip('\n') %}
-            {%- endif %}
-        {%- endif %}
-        {%- if loop.index0 > ns.last_query_index %}
-            {%- if loop.last or (not loop.last and reasoning_content) %}
-                {{- '<s>' + message.role + '\n<SPECIAL_11>\n' + reasoning_content.strip('\n') + '\n<SPECIAL_12>\n\n' + content.lstrip('\n') }}
-            {%- else %}
-                {{- '<s>' + message.role + '\n' + content }}
-            {%- endif %}
-        {%- else %}
-            {{- '<s>' + message.role + '\n' + content }}
-        {%- endif %}
-        {%- if message.tool_calls %}
-            {%- for tool_call in message.tool_calls %}
-                {%- if (loop.first and content) or (not loop.first) %}
-                    {{- '\n' }}
-                {%- endif %}
-                {%- if tool_call.function %}
-                    {%- set tool_call = tool_call.function %}
-                {%- endif %}
-                {{- '[TOOL_CALLS]\n{"name": "' }}
-                {{- tool_call.name }}
-                {{- '", "arguments": ' }}
-                {%- if tool_call.arguments is string %}
-                    {{- tool_call.arguments }}
-                {%- else %}
-                    {{- tool_call.arguments | tojson }}
-                {%- endif %}
-                {{- '}\n[SPECIAL_10]' }}
-            {%- endfor %}
-        {%- endif %}
-        {{- '</s>\n' }}
-    {%- elif message.role == "tool" %}
-        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
-            {{- '<s>user' }}
-        {%- endif %}
-        {{- '\n[TOOL_RESULTS]\n' }}
-        {{- content }}
-        {{- '\n[/TOOL_RESULTS]' }}
-        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
-            {{- '</s>\n' }}
-        {%- endif %}
-    {%- endif %}
-{%- endfor %}
-{%- if add_generation_prompt %}
-    {{- '<s>assistant\n' }}
-    {%- if enable_thinking is defined and enable_thinking is false %}
-        {{- '<SPECIAL_11>\n\n<SPECIAL_12>\n\n' }}
-    {%- endif %}
-{%- endif %}

+{{'<SPECIAL_10>System'}}{% for message in messages %}{% if message['role'] == 'system' %}{{'
+' + message['content'].strip()}}{% endif %}{% endfor %}{{'
+'}}{% for message in messages %}{% if message['role'] == 'user' %}{{ '
+<SPECIAL_11>User
+' + message['content'].strip() + '
+<SPECIAL_11>Assistant
+' }}{% elif message['role'] == 'assistant' %}{{ message['content'].strip() }}{% endif %}{% endfor %}

tokenizer_config.json CHANGED Viewed

@@ -8004,14 +8004,15 @@
       "special": true
     }
   },
-  "bos_token": null,
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
-  "errors": "replace",
   "extra_special_tokens": {},
-  "model_max_length": 131072,
-  "pad_token": "<unk>",
-  "split_special_tokens": false,
   "tokenizer_class": "PreTrainedTokenizerFast",
-  "unk_token": null
 }

       "special": true
     }
   },
+  "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>"
 }