Baichuan / Baichuan2#

Baichuan is a Chinese-English bilingual language model series from Baichuan Inc., featuring strong Chinese language performance.

Task

Text Generation

Architecture

BaiChuanForCausalLM

Parameters

7B – 13B

HF Org

baichuan-inc

Available Models#

  • Baichuan2-13B-Chat

  • Baichuan2-7B-Chat

  • Baichuan-7B

Architecture#

  • BaiChuanForCausalLM

Example HF Models#

Model

HF ID

Baichuan2 13B Chat

baichuan-inc/Baichuan2-13B-Chat

Baichuan 7B

baichuan-inc/Baichuan-7B

Example Recipes#

Recipe

Description

baichuan_2_7b_squad.yaml

SFT — Baichuan2 7B on SQuAD

baichuan_2_7b_squad_peft.yaml

LoRA — Baichuan2 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/baichuan/baichuan_2_7b_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/baichuan/baichuan_2_7b_squad.yaml

See the Installation Guide and LLM Fine-Tuning Guide.

Fine-Tuning#

See the LLM Fine-Tuning Guide.

Hugging Face Model Cards#