62 lines
2.4 KiB
Markdown
62 lines
2.4 KiB
Markdown
---
|
||
base_model: zed-industries/zeta
|
||
pipeline_tag: text-generation
|
||
inference: true
|
||
language:
|
||
- en
|
||
license: apache-2.0
|
||
model_creator: zed-industries
|
||
model_name: zeta
|
||
model_type: qwen2
|
||
datasets:
|
||
- zed-industries/zeta
|
||
quantized_by: brittlewis12
|
||
tags:
|
||
- qwen2
|
||
|
||
---
|
||
|
||
# Zeta GGUF
|
||
|
||
**Original model**: [Zeta](https://huggingface.co/zed-industries/zeta)
|
||
|
||
**Model creator**: [Zed Industries](https://huggingface.co/zed-industries)
|
||
|
||
> This is a fine-tuned version of Qwen2.5-Coder-7b for edit prediction support in Zed. Please, refer to the [zeta dataset](https://huggingface.co/datasets/zed-industries/zeta) to see how you can train this model yourself.
|
||
|
||
This repo contains GGUF format model files for Zed Industries’ Zeta model, powering their [new "Edit Prediction" feature](https://zed.dev/blog/edit-prediction) in their open source text editor, [Zed](https://zed.dev).
|
||
|
||
### What is GGUF?
|
||
|
||
GGUF is a file format for representing AI models. It is the third version of the format,
|
||
introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp.
|
||
Converted with llama.cpp build 4710 (revision [8a8c4ce](https://github.com/ggerganov/llama.cpp/commits/8a8c4ceb6050bd9392609114ca56ae6d26f5b8f5)),
|
||
using [autogguf-rs](https://github.com/brittlewis12/autogguf-rs).
|
||
|
||
### Prompt template: ChatML
|
||
|
||
```
|
||
<|im_start|>system
|
||
{{system_message}}<|im_end|>
|
||
<|im_start|>user
|
||
{{prompt}}<|im_end|>
|
||
<|im_start|>assistant
|
||
|
||
|
||
```
|
||
|
||
---
|
||
|
||
## Download & run with [cnvrs](https://twitter.com/cnvrsai) on iPhone, iPad, and Mac!
|
||
|
||
|
||
|
||
[cnvrs](https://testflight.apple.com/join/sFWReS7K) is the best app for private, local AI on your device:
|
||
- create & save **Characters** with custom system prompts & temperature settings
|
||
- download and experiment with any **GGUF model** you can [find on HuggingFace](https://huggingface.co/models?library=gguf)!
|
||
* or, use an API key with the chat completions-compatible model provider of your choice -- ChatGPT, Claude, Gemini, DeepSeek, & more!
|
||
- make it your own with custom **Theme colors**
|
||
- powered by Metal ⚡️ & [Llama.cpp](https://github.com/ggerganov/llama.cpp), with **haptics** during response streaming!
|
||
- **try it out** yourself today, on [Testflight](https://testflight.apple.com/join/sFWReS7K)!
|
||
- follow [cnvrs on twitter](https://twitter.com/cnvrsai) to stay up to date
|