Falcon#
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).
Task |
Text Generation |
Architecture |
|
Parameters |
7B – 40B |
HF Org |
Available Models#
Falcon-40B, Falcon-40B-Instruct
Falcon-7B, Falcon-7B-Instruct
Falcon-RW-7B
Falcon3-7B-Instruct
Architecture#
FalconForCausalLM
Example HF Models#
Model |
HF ID |
|---|---|
Falcon 7B |
|
Falcon 40B |
|
Falcon RW 7B |
Example Recipes#
Recipe |
Description |
|---|---|
SFT — Falcon3 7B Instruct on SQuAD |
|
LoRA — 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
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/falcon/falcon3_7b_instruct_squad.yaml
See the Installation Guide and LLM Fine-Tuning Guide.
Fine-Tuning#
See the LLM Fine-Tuning Guide.