maternion/sweep-next-edit-1.5B

maternion/ sweep-next-edit-1.5B

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)

Applications

Claude Code ollama launch claude --model maternion/sweep-next-edit-1.5B

Codex ollama launch codex --model maternion/sweep-next-edit-1.5B

OpenCode ollama launch opencode --model maternion/sweep-next-edit-1.5B

OpenClaw ollama launch openclaw --model maternion/sweep-next-edit-1.5B

Models

View all →

Name

1 model

Size

Context

Input

sweep-next-edit-1.5B:latest

1.5GB · 32K context window · Text · 2 weeks ago

sweep-next-edit-1.5B:latest

1.5GB

32K

Text

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)