license: llama2
language:
- en
pipeline_tag: text-generation
tags:
- code
- code llama
rift-coder-v0-7b
Table of Contents
- Model Summary
- Uses
- Integrations
- Installation and Getting Started
- Training Data, Sources, Details & Procedure
- Evaluation & Metrics
- Contact
- Ethical Considerations & Limitations
Model Summary
rift-coder-v0-7b is a finetune of Glaive AI's model glaive-coder-7b. We conducted the fine-tuning on a representative collection of indexed repositories for Python and TypeScript.
We use GGML to make rift-coder-v0-7b as accessible as possible on as much hardware as possible.
This model is designed to excel at contextual code editing while maintaining the ability to run on your device. It works best in Morph Labs' VS Code extension, Rift.
- Developed by: Morph Labs
- Partnered with: Nomic AI & Together AI
- Language(s) (NLP): English. Fine-Tuned on Python & TypeScript.
- License: Llama2
- Model Type: Derivative of Fine-Tuned Model ultimately trained on CodeLlama-7b-hf
Uses
We suggest usage of the model when working with Python or TypeScript, as our fine-tuning occurred with those contexts in mind. The model may find utility in other domains.
Integrations
We offer the ability to use rift-coder-v0-7b natively with the Rift extension for VS Code, our extension for enabling an AI-native language server. We designed Rift (GitHub link) to be open-source, private, secure, and on-device. rift-coder-v0-7b helps make that possible.
Installation and Getting Started
Training Data, Sources, Details and Procedure
Evaluation and Metrics
Contact
Ethical Considerations and Limitations
rift-coder-v0-7b, as with all Large Language Models, carries inherent risks with use. Testing has been solely conducted in English, and our testing has not been fully comprehensive nor could be fully comprehensive of all use scenarios. The model may be prone to producing inaccurate, unsatisfactory, or otherwise undesirable outputs, and thus we encourage all developers to test and tune to their specific use case prior to deployment.
We encourage you to check out Meta's Responsible Use Guide for Llama 2.