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

Merge pull request #18 from virtualramblas/main

Browse Source 
Added links to download pre-converted and pre-quantized CodeGen mono models.
This commit is contained in:
James Ravenscroft 2023-04-22 08:02:35 +01:00 committed by GitHub
commit 2ee6186aa7
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 5 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
README.md
View File

@ -26,7 +26,11 @@ You have 2 options for getting the model
#### Option A: Direct Download - Easy, Quickstart
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 350M, 2B and 6B parameters available - these models are pre-trained on `C`, `C++`, `Go`, `Java`, `JavaScript`, and `Python`
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 350M, 2B and 6B parameters available - these models are pre-trained on `C`, `C++`, `Go`, `Java`, `JavaScript`, and `Python`
Pre-converted and pre-quantized models for the `mono` family of CodeGen (pre-trained on `Python` only) are available for download in the Hugging Face Hub:
:hugs: [CodeGen 350M mono](https://huggingface.co/Guglielmo/CodeGen-350M-mono-ggml-quant)
:hugs: [CodeGen 2B mono](https://huggingface.co/Guglielmo/CodeGen-2B-mono-ggml-quant)
:hugs: [CodeGen 6B mono](https://huggingface.co/Guglielmo/CodeGen-6B-mono-ggml-quant)
#### Option B: Convert The Models Yourself - Hard, More Flexible