Model CoverageLarge Language Models (LLMs)

Falcon

View as Markdown

Falcon is a series of open language models from the Technology Innovation Institute (TII) in Abu Dhabi, known for being trained on a high-quality curated web corpus (RefinedWeb).

TaskText Generation
ArchitectureFalconForCausalLM
Parameters7B – 40B
HF Orgtiiuae

Available Models

  • Falcon-40B, Falcon-40B-Instruct
  • Falcon-7B, Falcon-7B-Instruct
  • Falcon-RW-7B
  • Falcon3-7B-Instruct

Architecture

  • FalconForCausalLM

Example HF Models

ModelHF ID
Falcon 7Btiiuae/falcon-7b
Falcon 40Btiiuae/falcon-40b
Falcon RW 7Btiiuae/falcon-rw-7b

Example Recipes

RecipeDescription
falcon3_7b_instruct_squad.yamlSFT — Falcon3 7B Instruct on SQuAD
falcon3_7b_instruct_squad_peft.yamlLoRA — Falcon3 7B 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/falcon/falcon3_7b_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/falcon/falcon3_7b_instruct_squad.yaml

See the Installation Guide and LLM Fine-Tuning Guide.

Fine-Tuning

See the LLM Fine-Tuning Guide.

Hugging Face Model Cards