Text Generation
Transformers
Safetensors
PyTorch
English
nemotron_labs_sigma
feature-extraction
nvidia
nemotron-labs
conversational
custom_code
Instructions to use nvidia/Nemotron-Labs-Sigma-3B-instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nvidia/Nemotron-Labs-Sigma-3B-instruct with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="nvidia/Nemotron-Labs-Sigma-3B-instruct", trust_remote_code=True) messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("nvidia/Nemotron-Labs-Sigma-3B-instruct", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use nvidia/Nemotron-Labs-Sigma-3B-instruct with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "nvidia/Nemotron-Labs-Sigma-3B-instruct" # 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-Sigma-3B-instruct", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/nvidia/Nemotron-Labs-Sigma-3B-instruct
- SGLang
How to use nvidia/Nemotron-Labs-Sigma-3B-instruct 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-Sigma-3B-instruct" \ --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-Sigma-3B-instruct", "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-Sigma-3B-instruct" \ --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-Sigma-3B-instruct", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use nvidia/Nemotron-Labs-Sigma-3B-instruct with Docker Model Runner:
docker model run hf.co/nvidia/Nemotron-Labs-Sigma-3B-instruct
Point evaluation results at the technical report; document the per-task prompting convention
Browse files
README.md
CHANGED
|
@@ -165,10 +165,19 @@ Below roughly 16 steps the pretrained models lose quality noticeably; for few-st
|
|
| 165 |
prefer the distilled `-distill-*` variants, which are trained for a fixed step count and need
|
| 166 |
neither guidance nor score-temperature tuning.
|
| 167 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 168 |
## Evaluation Results
|
| 169 |
|
| 170 |
-
|
| 171 |
-
|
|
|
|
| 172 |
|
| 173 |
## Training, Testing, and Evaluation Datasets
|
| 174 |
|
|
|
|
| 165 |
prefer the distilled `-distill-*` variants, which are trained for a fixed step count and need
|
| 166 |
neither guidance nor score-temperature tuning.
|
| 167 |
|
| 168 |
+
### Prompting convention
|
| 169 |
+
|
| 170 |
+
Use the chat template for conversational and reasoning tasks (see the example
|
| 171 |
+
above). For code-completion benchmarks such as HumanEval and MBPP, pass the raw
|
| 172 |
+
prompt **without** the chat template: those tasks hand the model a function
|
| 173 |
+
signature to continue, and wrapping them in a chat turn makes the model answer
|
| 174 |
+
conversationally instead of completing the code.
|
| 175 |
+
|
| 176 |
## Evaluation Results
|
| 177 |
|
| 178 |
+
Benchmark results for this model family, averaged over multiple generation
|
| 179 |
+
seeds, are reported in the technical report:
|
| 180 |
+
[Large Language Continuous Diffusion Models](https://arxiv.org/abs/2610.02665).
|
| 181 |
|
| 182 |
## Training, Testing, and Evaluation Datasets
|
| 183 |
|