OLMo2#
OLMo2 is Allen AI’s second-generation open language model with improved architecture and training, including RMSNorm and rotary position embeddings.
Task |
Text Generation |
Architecture |
|
Parameters |
1B – 13B |
HF Org |
Available Models#
OLMo2-0425-1B-Instruct
OLMo2-7B-1124
OLMo2-13B-1124
Architecture#
OLMo2ForCausalLM
Example HF Models#
Model |
HF ID |
|---|---|
OLMo2 7B |
|
OLMo2 0425 1B Instruct |
Example Recipes#
Recipe |
Description |
|---|---|
SFT — OLMo2 0425 1B Instruct on SQuAD |
|
LoRA — OLMo2 0425 1B Instruct on SQuAD |
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/olmo/olmo_2_0425_1b_instruct_squad.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/olmo/olmo_2_0425_1b_instruct_squad.yaml
See the Installation Guide and LLM Fine-Tuning Guide.
Fine-Tuning#
See the LLM Fine-Tuning Guide.