Model CoverageLarge Language Models

Command-R

View as Markdown

Cohere Command-R is a series of enterprise-grade language models optimized for retrieval-augmented generation (RAG) and tool use. Command-R7B uses the updated Cohere2ForCausalLM architecture.

TaskText Generation
ArchitectureCohereForCausalLM / Cohere2ForCausalLM
Parameters7B – 104B
HF OrgCohereForAI

Available Models

  • c4ai-command-r-v01: 35B
  • c4ai-command-r-plus: 104B
  • c4ai-command-r7b-12-2024: 7B (Cohere2ForCausalLM)

Architectures

  • CohereForCausalLM — Command-R v01, Plus
  • Cohere2ForCausalLM — Command-R7B

Example HF Models

Example Recipes

RecipeDescription
cohere_command_r_7b_squad.yamlSFT — Command-R 7B on SQuAD
cohere_command_r_7b_squad_peft.yamlLoRA — Command-R 7B 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/cohere/cohere_command_r_7b_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:26.06.00

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/cohere/cohere_command_r_7b_squad.yaml

See the Installation Guide and LLM Fine-Tuning Guide.

Fine-Tuning

See the LLM Fine-Tuning Guide.

Hugging Face Model Cards