Model CoverageLarge Language Models (LLMs)

OLMo2

View as Markdown

OLMo2 is Allen AI’s second-generation open language model with improved architecture and training, including RMSNorm and rotary position embeddings.

TaskText Generation
ArchitectureOLMo2ForCausalLM
Parameters1B – 13B
HF Orgallenai

Available Models

  • OLMo2-0425-1B-Instruct
  • OLMo2-7B-1124
  • OLMo2-13B-1124

Architecture

  • OLMo2ForCausalLM

Example HF Models

ModelHF ID
OLMo2 7Ballenai/OLMo2-7B-1124
OLMo2 0425 1B Instructallenai/OLMo2-0425-1B-Instruct

Example Recipes

RecipeDescription
olmo_2_0425_1b_instruct_squad.yamlSFT — OLMo2 0425 1B Instruct on SQuAD
olmo_2_0425_1b_instruct_squad_peft.yamlLoRA — 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

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:26.04.00

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.

Hugging Face Model Cards