Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Update README.md #461

Open
wants to merge 4 commits into
base: main
Choose a base branch
from
Open

Update README.md #461

Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
9d9fc63
Update README.md
avie66 Oct 30, 2024
283d3d2
Update README.md
avie66 Nov 1, 2024
0e85d40
Update README.md
avie66 Dec 11, 2024
61923cb
Update README.md
avie66 Dec 11, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
131 changes: 83 additions & 48 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,7 @@
</picture>
</p>

This repo consists Refact WebUI for fine-tuning and self-hosting of code models, that you can later use inside Refact plugins for code completion and chat.
This repository contains the Refact WebUI, designed for fine-tuning and self-hosting of code models. You can seamlessly integrate these models into Refact plugins for enhanced code completion and chat capabilities.

---

Expand All @@ -15,17 +15,49 @@ This repo consists Refact WebUI for fine-tuning and self-hosting of code models,
[![Visual Studio](https://img.shields.io/visual-studio-marketplace/d/smallcloud.codify?label=VS%20Code)](https://marketplace.visualstudio.com/items?itemName=smallcloud.codify)
[![JetBrains](https://img.shields.io/jetbrains/plugin/d/com.smallcloud.codify?label=JetBrains)](https://plugins.jetbrains.com/plugin/20647-codify)

- [x] Fine-tuning of open-source code models
- [x] Self-hosting of open-source code models
- [x] Download and upload Lloras
- [x] Use models for code completion and chat inside Refact plugins
- [x] Model sharding
- [x] Host several small models on one GPU
- [x] Use OpenAI and Anthropic keys to connect GPT-models for chat
## Key Features 🌟

![self-hosting-refact](https://github.com/smallcloudai/refact/assets/5008686/18e48b42-b638-4606-bde0-cadd47fd26e7)
avie66 marked this conversation as resolved.
Show resolved Hide resolved
- ✅ Fine-tuning of open-source code models
- ✅ Self-hosting of open-source code models
- ✅ Download and upload Lloras
- ✅ Use models for code completion and chat inside Refact plugins
- ✅ Model sharding
- ✅ Host several small models on one GPU
- ✅ Use OpenAI and Anthropic keys to connect GPT models for chat

---

# Demo Video 🎥

This would be added soon

---

# Table of Contents 📚

- [Custom Installation](#custom-installation-%EF%B8%8F)
- [Running Refact Self-Hosted in a Docker Container](#running-refact-self-hosted-in-a-docker-container-)
- [Getting Started with Plugins](#getting-started-with-plugins-)
- [Supported Models](#supported-models-)
- [Contributing](#contributing-)
- [Follow Us/FAQ](#follow-us-and-faq-)
- [License](#license-)


# Custom Installation ⚙️

You can also install refact repo without docker:
```shell
pip install .
```
If you have a GPU with CUDA capability >= 8.0, you can also install it with flash-attention v2 support:
```shell
FLASH_ATTENTION_FORCE_BUILD=TRUE MAX_JOBS=4 INSTALL_OPTIONAL=TRUE pip install .
```


## Running Refact Self-Hosted in a Docker Container 🐳

### Running Refact Self-Hosted in a Docker Container

The easiest way to run the self-hosted server is a pre-build Docker image.

Expand Down Expand Up @@ -82,11 +114,12 @@ docker volume rm VVV
```
</details>

See [CONTRIBUTING.md](CONTRIBUTING.md) for installation without a docker container.

See [CONTRIBUTING.md](CONTRIBUTING.md) for installation without a docker container.

---

### Setting Up Plugins
# Getting Started with Plugins 🔌


Download Refact for [VS Code](https://marketplace.visualstudio.com/items?itemName=smallcloud.codify) or [JetBrains](https://plugins.jetbrains.com/plugin/20647-refact-ai).
Expand All @@ -97,53 +130,55 @@ Go to plugin settings and set up a custom inference URL `http://127.0.0.1:8008`
Settings > Tools > Refact.ai > Advanced > Inference URL
</details>
<details><summary>VSCode</summary>
Extensions > Refact.ai Assistant > Settings > Infurl
Extensions > Refact.ai Assistant > Settings > Address URL
</details>

---

## Supported models
## Supported Models 📊

| Model | Completion | Chat | Fine-tuning | [Deprecated](## "Will be removed in next versions") |
|---------------------------------------------------------------------------------------------------|------------|------|-------------|-----------------------------------------------------|
| [Refact/1.6B](https://huggingface.co/smallcloudai/Refact-1_6B-fim) | + | | + | |
| [starcoder2/3b/base](https://huggingface.co/bigcode/starcoder2-3b) | + | | + | |
| [starcoder2/7b/base](https://huggingface.co/bigcode/starcoder2-7b) | + | | + | |
| [starcoder2/15b/base](https://huggingface.co/bigcode/starcoder2-15b) | + | | + | |
| [deepseek-coder/1.3b/base](https://huggingface.co/deepseek-ai/deepseek-coder-1.3b-base) | + | | + | |
| [deepseek-coder/5.7b/mqa-base](https://huggingface.co/deepseek-ai/deepseek-coder-5.7bmqa-base) | + | | + | |
| [magicoder/6.7b](https://huggingface.co/TheBloke/Magicoder-S-DS-6.7B-GPTQ) | | + | | |
| [mistral/7b/instruct-v0.1](https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.1-GPTQ) | | + | | |
| [mixtral/8x7b/instruct-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1) | | + | | |
| [deepseek-coder/6.7b/instruct](https://huggingface.co/TheBloke/deepseek-coder-6.7B-instruct-GPTQ) | | + | | |
| [deepseek-coder/33b/instruct](https://huggingface.co/deepseek-ai/deepseek-coder-33b-instruct) | | + | | |
| [stable/3b/code](https://huggingface.co/stabilityai/stable-code-3b) | + | | | |
| [llama3/8b/instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) | | + | | |

## Usage

Refact is free to use for individuals and small teams under BSD-3-Clause license. If you wish to use Refact for Enterprise, please [contact us](https://refact.ai/contact/).

## Custom installation
| [Refact/1.6B](https://huggingface.co/smallcloudai/Refact-1_6B-fim) | ✅ | ❌ | ✅ | |
| [starcoder2/3b/base](https://huggingface.co/bigcode/starcoder2-3b) | ✅ | ❌ | ✅ | |
| [starcoder2/7b/base](https://huggingface.co/bigcode/starcoder2-7b) | ✅ | ❌ | ✅ | |
| [starcoder2/15b/base](https://huggingface.co/bigcode/starcoder2-15b) | ✅ | ❌ | ✅ | ✅ |
| [deepseek-coder/1.3b/base](https://huggingface.co/deepseek-ai/deepseek-coder-1.3b-base) | ✅ | ❌ | ✅ | ✅ |
| [deepseek-coder/5.7b/mqa-base](https://huggingface.co/deepseek-ai/deepseek-coder-5.7bmqa-base) | ✅ | ❌ | ✅ | ✅ |
| [magicoder/6.7b](https://huggingface.co/TheBloke/Magicoder-S-DS-6.7B-GPTQ) | ❌ | ✅ | ❌ | ✅ |
| [mistral/7b/instruct-v0.1](https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.1-GPTQ) | ❌ | ✅ | ❌ | ✅ |
| [mixtral/8x7b/instruct-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1) | ❌ | ✅ | ❌ | |
| [deepseek-coder/6.7b/instruct](https://huggingface.co/TheBloke/deepseek-coder-6.7B-instruct-GPTQ) | ❌ | ✅ | ❌ | |
| [deepseek-coder/33b/instruct](https://huggingface.co/deepseek-ai/deepseek-coder-33b-instruct) | ❌ | ✅ | ❌ | |
| [stable/3b/code](https://huggingface.co/stabilityai/stable-code-3b) | ✅ | ❌ | ❌ | |
| [llama3/8b/instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) | ❌ | ✅ | ❌ | |

You can also install refact repo without docker:
```shell
pip install .
```
If you have a GPU with CUDA capability >= 8.0, you can also install it with flash-attention v2 support:
```shell
FLASH_ATTENTION_FORCE_BUILD=TRUE MAX_JOBS=4 INSTALL_OPTIONAL=TRUE pip install .
```
---


# Contributing 🤝

## FAQ
If you wish to contribute to this project, feel free to explore our [current issues](https://github.com/smallcloudai/refact/issues) or open new issues related to (bugs/features) using our [CONTRIBUTING.md](CONTRIBUTING.md).


---

Q: Can I run a model on CPU?
## Follow Us and FAQ ❓

A: it doesn't run on CPU yet, but it's certainly possible to implement this.
**Q: Can I run a model on CPU?**

## Community & Support
A: Currently, it doesn't run on CPU, but it's certainly possible to implement this.

- Contributing [CONTRIBUTING.md](CONTRIBUTING.md)
- [GitHub issues](https://github.com/smallcloudai/refact/issues) for bugs and errors
- [Community forum](https://github.com/smallcloudai/refact/discussions) for community support and discussions
- [Contributing](CONTRIBUTING.md)
- [Refact Docs](https://docs.refact.ai/guides/version-specific/self-hosted/)
- [GitHub Issues](https://github.com/smallcloudai/refact/issues) for bugs and errors
- [Community Forum](https://github.com/smallcloudai/refact/discussions) for community support and discussions
- [Discord](https://www.smallcloud.ai/discord) for chatting with community members
- [Twitter](https://twitter.com/refact_ai) for product news and updates

---

## License 📜

Refact is free to use for individuals and small teams under the BSD-3-Clause license. If you wish to use Refact for Enterprise, please [contact us](https://refact.ai/contact/).