代码拉取完成,页面将自动刷新
LLaMA2 is a large language model released by Meta in 2023, with parameters ranging from 7B to 70B. Compared to LLaMA, the training corpus of LLaMA2 is 40% longer, and the context length has been upgraded from 2048 to 4096, allowing for understanding and generating longer texts.
cd deepsparkhub/nlp/llm/llama2-7b_reward_sft/deepspeed
pip install -r requirements.txt
pip install -e .
Prepare datasets and pretrained model weight
# Install lfs
wget https://packagecloud.io/github/git-lfs/packages/el/7/git-lfs-2.13.2-1.el7.x86_64.rpm/download -O lfs.rpm
rpm -ivh lfs.rpm
rm -y lfs.rpm
git lfs install
# Get Dahoas/rm-static
mkdir -p datasets/Dahoas && cd datasets/Dahoas
git clone https://huggingface.co/datasets/Dahoas/rm-static
# Get Llama-2-7b-hf pretraining weights
- [Huggingface](https://huggingface.co/meta-llama/Llama-2-7b-hf)
- [aifasthub](https://aifasthub.com/models/NousResearch/Llama-2-7b-hf)
mv Llama-2-7b-hf/ datasets/
Fine-tuning
cd training/step2_reward_model_finetuning/training_scripts/llama2/
bash ./run_llama2_7b.sh
GPUs | Epochs | FPS | ACC |
---|---|---|---|
BI-V100 x8 | 1 | AvgSamplesPerSec: 1.948 | 0.6821 |
此处可能存在不合适展示的内容,页面不予展示。您可通过相关编辑功能自查并修改。
如您确认内容无涉及 不当用语 / 纯广告导流 / 暴力 / 低俗色情 / 侵权 / 盗版 / 虚假 / 无价值内容或违法国家有关法律法规的内容,可点击提交进行申诉,我们将尽快为您处理。