Model CoverageEmbedding ModelsMetaLlama-3.2-1B

Llama-3.2-1B

View as Markdown

Llama-3.2-1B has a checked-in NeMo AutoModel recipe for feature extraction. The Hugging Face configuration declares the LlamaForCausalLM architecture.

Fine-Tune Llama-3.2-1B

Follow the installation instructions, then run the recipe from the repository root:

uv run automodel examples/retrieval/bi_encoder/llama3_2_1b.yaml --nproc-per-node 8

Choose a Workflow

GoalStart Here
Run the primary recipe for this modelUse the recipe configuration.
Prepare your environmentFollow the installation instructions.

Configuration

SettingConfiguration
Hardware-
StrategyFSDP2; tp_size=1, cp_size=1
Nodes1
FeaturesCheckpointing (enabled=true)
Advancedbfloat16

Model Reference

Model Architecture

PropertyValue
TaskFeature extraction
ArchitectureLlamaForCausalLM

Available Models