GPT-OSS#
GPT-OSS is OpenAI’s open-weight model family featuring QuickGELU activations and activation clamping for training stability.
Task |
Text Generation |
Architecture |
|
Parameters |
20B – 120B |
HF Org |
Available Models#
gpt-oss-20b: 20B parameters
gpt-oss-120b: 120B parameters
Architecture#
GptOssForCausalLM
Example HF Models#
Model |
HF ID |
|---|---|
GPT-OSS 20B |
|
GPT-OSS 120B |
Example Recipes#
Recipe |
Description |
|---|---|
SFT — GPT-OSS 20B |
|
SFT — GPT-OSS 120B |
Try with NeMo AutoModel#
1. Install (full instructions):
pip install nemo-automodel
2. Clone the repo to get the example recipes:
git clone https://github.com/NVIDIA-NeMo/Automodel.git
cd Automodel
3. Run the recipe from inside the repo:
automodel --nproc-per-node=8 examples/llm_finetune/gpt_oss/gpt_oss_20b.yaml
Run with Docker
1. Pull the container and mount a checkpoint directory:
docker run --gpus all -it --rm \
--shm-size=8g \
-v $(pwd)/checkpoints:/opt/Automodel/checkpoints \
nvcr.io/nvidia/nemo-automodel:26.02.00
2. Navigate to the AutoModel directory (where the recipes are):
cd /opt/Automodel
3. Run the recipe:
automodel --nproc-per-node=8 examples/llm_finetune/gpt_oss/gpt_oss_20b.yaml
See the Installation Guide and LLM Fine-Tuning Guide.
Fine-Tuning#
See the LLM Fine-Tuning Guide.