update evaluation infos

README.md

@@ -22,14 +22,14 @@ Llama-3中选择了一个相对标准的decoder-only的transformer架构。与Ll
 ### Docker（方法一）
 
 ```bash
-docker pull image.sourcefind.cn:5000/dcu/admin/base/pytorch:2.1.0-centos7.6-dtk23.10.1-py38
+docker pull image.sourcefind.cn:5000/dcu/admin/base/pytorch:2.1.0-ubuntu22.04-dtk23.10.1-py310
 docker run -it -v /path/your_code_data/:/path/your_code_data/ -v /opt/hyhal/:/opt/hyhal/:ro --shm-size=32G --privileged=true --device=/dev/kfd --device=/dev/dri/ --group-add video --name docker_name imageID bash
 
 cd /your_code_path/llama3_pytorch
 
 pip install -e .
 
-pip install deepspeed-0.12.3+git299681e.abi0.dtk2310.torch2.1.0a0-cp38-cp38-manylinux2014_x86_64.whl
+pip install deepspeed-0.12.3+gitfe61783.abi0.dtk2310.torch2.1.0a0-cp310-cp310-manylinux2014_x86_64.whl
 pip install bitsandbytes-0.43.0-py3-none-any.whl
 pip install -U xtuner # 0.1.18
 pip install mmengine==0.10.3
@@ -46,7 +46,7 @@ cd /your_code_path/llama3_pytorch
 
 pip install -e .
 
-pip install deepspeed-0.12.3+git299681e.abi0.dtk2310.torch2.1.0a0-cp38-cp38-manylinux2014_x86_64.whl
+pip install deepspeed-0.12.3+gitfe61783.abi0.dtk2310.torch2.1.0a0-cp310-cp310-manylinux2014_x86_64.whl
 pip install bitsandbytes-0.43.0-py3-none-any.whl
 pip install -U xtuner # 0.1.18
 pip install mmengine==0.10.3
@@ -56,7 +56,7 @@ pip install mmengine==0.10.3
 关于本项目DCU显卡所需的特殊深度学习库可从[光合](https://developer.hpccube.com/tool/)开发者社区下载安装。
 ```bash
 DTK驱动: dtk23.10.1
-python: python3.8
+python: python3.10
 torch: 2.1.0
 xtuner: 0.1.18
 ```
@@ -66,7 +66,7 @@ xtuner: 0.1.18
 ```bash
 pip install -e .
 
-pip install deepspeed-0.12.3+git299681e.abi0.dtk2310.torch2.1.0a0-cp38-cp38-manylinux2014_x86_64.whl
+pip install deepspeed-0.12.3+gitfe61783.abi0.dtk2310.torch2.1.0a0-cp310-cp310-manylinux2014_x86_64.whl
 pip install bitsandbytes-0.43.0-py3-none-any.whl
 pip install -U xtuner # 0.1.18
 pip install mmengine==0.10.3
@@ -141,6 +141,32 @@ torchrun --nproc_per_node 1 example_chat_completion.py \
     --max_seq_len 512 --max_batch_size 6
 ```
 
+## 验证
+1. 安装 `llama-recipes`、`lm-eval` 库
+```bash
+# llama-recipes 下载
+git clone https://github.com/meta-llama/llama-recipes.git
+cd ./llama-recipes/recipes/evaluation/
+# 修改eval.py第15行代码，将from lm_eval.utils import make_table 改为
+from lm_eval.evaluator import make_table
+# 修改eval.py第121行代码，num_fewshot参数的默认值改为0
+default=0
+
+# 返回根目录
+cd ~
+# lm-eval 下载
+git clone http://developer.hpccube.com/codes/chenych/lm-evaluation-harness.git
+cd ./lm-evaluation-harness/
+pip install -e .
+cd ../
+```
+
+2. 修改待测模型**pretrained**参数地址，例如 `/home/Meta-Llama-3-8B-Instruct`，特别地，当前仅支持`hellaswag`数据集进行测试验证。执行以下命令:
+```bash
+cd /path/of/llama-recipes/recipes/evaluation
+python eval.py --model hf --model_args pretrained=/home/llama3/Meta-Llama-3-8B-Instruct,dtype="float" --tasks hellaswag --device cuda --batch_size 8
+```
+
 ## result
 - Meta-Llama-3-8B-Instruct
 <div align=center>

docker/Dockerfile

-FROM image.sourcefind.cn:5000/dcu/admin/base/pytorch:2.1.0-centos7.6-dtk23.10.1-py38
+FROM image.sourcefind.cn:5000/dcu/admin/base/pytorch:2.1.0-ubuntu22.04-dtk23.10.1-py310
\ No newline at end of file