Model CoverageLarge Language Models

Bamba

View as Markdown

Bamba is a hybrid SSM-attention language model from IBM, combining Mamba-2 selective state space layers with standard transformer attention for efficient long-context processing.

TaskText Generation
ArchitectureBambaForCausalLM
Parameters9B
HF Orgibm-ai-platform

Available Models

  • Bamba-9B: 9B parameters

Architecture

  • BambaForCausalLM

Example HF Models

ModelHF ID
Bamba 9Bibm-ai-platform/Bamba-9B

Try with NeMo AutoModel

Install NeMo AutoModel and follow the fine-tuning guide to configure a recipe for this model.

1. Clone and install from source (full instructions):

git clone https://github.com/NVIDIA-NeMo/Automodel.git
cd Automodel
uv sync --locked --all-groups --all-extras

2. Fine-tune by adapting a base LLM recipe — override the model ID on the CLI:

uv run automodel --nproc-per-node=8 examples/llm_finetune/llama3_2/llama3_2_1b_squad.yaml \
  --model.pretrained_model_name_or_path "<MODEL_HF_ID>"

Replace <MODEL_HF_ID> with the model ID from Example HF Models above.

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:26.06.00

2. The recipes are at /opt/Automodel/examples/ — navigate there:

cd /opt/Automodel

3. Fine-tune:

automodel --nproc-per-node=8 examples/llm_finetune/llama3_2/llama3_2_1b_squad.yaml \
  --model.pretrained_model_name_or_path "<MODEL_HF_ID>"

See the Installation Guide and LLM Fine-Tuning Guide.

Fine-Tuning

See the LLM Fine-Tuning Guide.

Hugging Face Model Cards