AI/turbopilot
1
0
Fork 0
mirror of https://github.com/ravenscroftj/turbopilot.git synced 2024-10-01 01:06:01 -04:00
Code Issues Packages Projects Releases Wiki Activity

Add instructions for getting the models

Browse Source
This commit is contained in:
James Ravenscroft 2023-04-10 09:39:58 +01:00
parent 809e312384
commit a1eb846d88
1 changed files with 23 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

32
README.md
View File

@ -20,30 +20,41 @@ make codegen codegen-quantize
## Getting The Models
### Direct Access
### Direct Download
You can download the pre-converted, pre-quantized models from [Google Drive](https://drive.google.com/drive/folders/1wFy1Y0pqoK23ZeMWWCp8evxWOJQVdaGh?usp=sharing)
You can download the pre-converted, pre-quantized models from [Google Drive](https://drive.google.com/drive/folders/1wFy1Y0pqoK23ZeMWWCp8evxWOJQVdaGh?usp=sharing). I've made the `multi` flavour models with 2B and 6B parameters available - these models are pre-trained on `C`, `C++`, `Go`, `Java`, `JavaScript`, and `Python`
### Convert The Models Yourself
Start by downloading either the [2B](https://huggingface.co/moyix/codegen-2B-multi-gptj) or [6B](https://huggingface.co/moyix/codegen-6B-multi-gptj) GPT-J versions of CodeGen.
You could also experiment with the other sizes of model such as [16B](https://huggingface.co/moyix/codegen-16B-multi-gptj) if you want or try the mono models ([2B](https://huggingface.co/moyix/codegen-2B-mono-gptj), [6B](https://huggingface.co/moyix/codegen-6B-mono-gptj), [16B](https://huggingface.co/moyix/codegen-16B-mono-gptj)) which are fine-tuned on python only but which outperform the `multi` models in some cases (see [the original paper](https://arxiv.org/pdf/2203.13474.pdf) for details).
You will also need to place [vocab.json](https://huggingface.co/Salesforce/codegen-2B-multi/raw/main/vocab.json) and [added_tokens.json](https://huggingface.co/Salesforce/codegen-2B-multi/blob/main/added_tokens.json) in the directory along with the model to make the conversion script work. This is a temporary limitation that I'll remove at some point.
You can directly `git clone` from huggingface URLS above. To save time you can disable LFS on first checkout and selectively pull the files you need (you only need the `.bin` files for conversion. The large `.zst` files are not needed). Here is an example:
```bash
GIT_LFS_SKIP_SMUDGE=1 git clone https://huggingface.co/moyix/codegen-16B-multi-gptj
git config lfs.fetchexclude "*.zst"
git lfs fetch
git lfs checkout *.bin
```
#### Install Python Dependencies
The `convert-codegen-to-ggml.py` requires Python 3 - I used `3.10`. Install the dependencies with `pip install -r requirements.txt`.
#### Convert The Model
```bash
python convert-codegen-to-ggml.py ./codegen-6B-multi-gptj 0
```
#### Quantize the model
#### Quantize the Model
```bash
./bin/codegen-quantize ../../codegen-6B-multi-gptj/ggml-model-f32.bin ../../codegen-6B-multi-gptj/ggml-model-quant.bin 2
```
## Run the model
```bash
./bin/codegen -t 6 -m ../../codegen-6B-multi-gptj/ggml-model-quant.bin -p "def main("
./bin/codegen-quantize ./codegen-6B-multi-gptj/ggml-model-f32.bin ./codegen-6B-multi-gptj/ggml-model-quant.bin 2
```
@ -55,3 +66,4 @@ python convert-codegen-to-ggml.py ./codegen-6B-multi-gptj 0
- The project uses the [Salesforce Codegen](https://github.com/salesforce/CodeGen) models.
- Thanks to [Moyix](https://huggingface.co/moyix) for his work on converting the Salesforce models to run in a GPT-J architecture. Not only does this [confer some speed benefits](https://gist.github.com/moyix/7896575befbe1b99162ccfec8d135566) but it also made it much easier for me to port the models to GGML using the [existing gpt-j example code](https://github.com/ggerganov/ggml/tree/master/examples/gpt-j)
- The model server uses [CrowCPP](https://crowcpp.org/master/) to serve suggestions.
- Check out the [original scientific paper](https://arxiv.org/pdf/2203.13474.pdf) for CodeGen for more info.