maternion/sweep-next-edit-1.5B

maternion/ sweep-next-edit-1.5B:latest

145 Downloads Updated 2 weeks ago

Sweep Next-Edit a 1.5B parameter model for next-edit autocomplete, quantized to Q8_0 GGUF format. (Template supports tools)

tools

ollama run maternion/sweep-next-edit-1.5B

curl http://localhost:11434/api/chat \
  -d '{
    "model": "maternion/sweep-next-edit-1.5B",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='maternion/sweep-next-edit-1.5B',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'maternion/sweep-next-edit-1.5B',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 2 weeks ago

2 weeks ago

6a6bbfafb2cf · 1.5GB ·

model

archqwen2

parameters1.45B

quantizationQ8_0

1.5GB

template

{{- if .Messages }} {{- if or .System .Tools }}<|im_start|>system {{- if .System }} {{ .System }} {{

1.5kB

Readme

Model Description

Sweep Next-Edit predicts your next code edit before you make it. It runs locally on your laptop in under 500ms (with speculative decoding) and outperforms models over 4x its size on next-edit benchmarks. More details here.

Usage

Download ollama and then:

ollama run maternion/sweep-next-edit-1.5B

Model Details

Format: GGUF (Q8_0 quantization)
Parameters: 1.5B
Context Length: 8192 tokens
Base Model: Qwen2.5-Coder

Example

The model uses a specific prompt format with file context, recent diffs, and current state to predict the next edit.

License

Apache 2.0

## Model Description

## Usage

Download [ollama](https://ollama.com/download) and then:

```bash
ollama run maternion/sweep-next-edit-1.5B
```

## Model Details

- **Format**: GGUF (Q8_0 quantization)
- **Parameters**: 1.5B
- **Context Length**: 8192 tokens
- **Base Model**: Qwen2.5-Coder

## Example

The model uses a specific prompt format with file context, recent diffs, and current state to predict the next edit.

## Links

- [Blog Post](https://blog.sweep.dev/posts/oss-next-edit) - Technical details and benchmarks
- [JetBrains Plugin](https://plugins.jetbrains.com/plugin/26860-sweep-ai-autocomplete--coding-agent) - Sweep AI JetBrains Plugin
- [HN Thread](https://news.ycombinator.com/item?id=46713106) - Discuss implementation for VSCode, Neovim & Emacs
- [Twitter Post](https://x.com/sweepai/status/2014045512417345883) - Ask us any other questions

## License

Apache 2.0

Paste, drop or click to upload images (.png, .jpeg, .jpg, .svg, .gif)