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

added acknowledgement of crow

Browse Source
This commit is contained in:
James Ravenscroft 2023-04-10 09:21:58 +01:00
parent 22b0f9664f
commit fb5ef23564
1 changed files with 10 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
README.md
View File

@ -20,15 +20,21 @@ make codegen codegen-quantize
## Getting The Models ## Getting The Models
### Direct Access
You can download the pre-converted, pre-quantized models from [Google Drive](https://drive.google.com/drive/folders/1wFy1Y0pqoK23ZeMWWCp8evxWOJQVdaGh?usp=sharing)
### 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. 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.
## Convert The Model #### Convert The Model
```bash ```bash
python convert-codegen-to-ggml.py ./codegen-6B-multi-gptj 0 python convert-codegen-to-ggml.py ./codegen-6B-multi-gptj 0
``` ```
## Quantize the model #### Quantize the model
```bash ```bash
./bin/codegen-quantize ../../codegen-6B-multi-gptj/ggml-model-f32.bin ../../codegen-6B-multi-gptj/ggml-model-quant.bin 2 ./bin/codegen-quantize ../../codegen-6B-multi-gptj/ggml-model-f32.bin ../../codegen-6B-multi-gptj/ggml-model-quant.bin 2
@ -48,3 +54,4 @@ python convert-codegen-to-ggml.py ./codegen-6B-multi-gptj 0
- The frontend of the project is powered by [Venthe's vscode-fauxpilot plugin](https://github.com/Venthe/vscode-fauxpilot) - The frontend of the project is powered by [Venthe's vscode-fauxpilot plugin](https://github.com/Venthe/vscode-fauxpilot)
- The project uses the [Salesforce Codegen](https://github.com/salesforce/CodeGen) models. - 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) - 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.