mirrors/LLM4Decompile
2
0
Fork 0
mirror of https://github.com/albertan017/LLM4Decompile.git synced 2026-06-17 01:55:50 +00:00
Code Issues Projects Releases Packages Wiki Activity

Update README.md

Browse source
This commit is contained in:
albertan017 2024-06-18 20:38:50 +08:00 • committed by GitHub
commit f763df7ee4
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 21 additions and 18 deletions
Download patch file Download diff file Expand all files Collapse all files

39
evaluation/README.md
View file

@ -2,25 +2,8 @@
* [2023-05-16]: Please use ``decompile-eval-executable-gcc-obj.json``. The source codes are compiled into executable binaries and disassembled into assembly instructions.
* [2023-04-10]: Add vllm evaluation script.
---
To run the evaluation on single GPU and single process:
```bash
cd LLM4Decompile
python ./evaluation/run_evaluation_llm4decompile_singleGPU.py
```
---
To run the evaluation using TGI (10x faster, support multiple GPUs and multi-process):
First, please install the text-generation-inference following the official [link](https://github.com/huggingface/text-generation-inference)
```bash
git clone https://github.com/albertan017/LLM4Decompile.git
cd LLM4Decompile
pip install -r requirements.txt
# Before running the evaluation script, please update the model_path to your local model path.
bash ./scripts/run_evaluation_llm4decompile.sh
```
---
To run the evaluation using [vLLM](https://github.com/vllm-project/vllm)
To run the evaluation using [vLLM](https://github.com/vllm-project/vllm) (**Recommended**)
```bash
pip install -r requirements.txt
```
@ -40,3 +23,23 @@ python run_evaluation_llm4decompile_vllm.py \
--temperature 0
```
---
To run the evaluation on single GPU and single process:
```bash
cd LLM4Decompile
python ./evaluation/run_evaluation_llm4decompile_singleGPU.py
```
---
To run the evaluation using TGI (10x faster, support multiple GPUs and multi-process):
First, please install the text-generation-inference following the official [link](https://github.com/huggingface/text-generation-inference)
```bash
git clone https://github.com/albertan017/LLM4Decompile.git
cd LLM4Decompile
pip install -r requirements.txt
# Before running the evaluation script, please update the model_path to your local model path.
bash ./scripts/run_evaluation_llm4decompile.sh
```
---