---
title: ichigo-0.5
canonical_url: "https://www.modelscope.cn/models/cortexso/ichigo-0.5"
md_url: "https://www.modelscope.cn/models/cortexso/ichigo-0.5.md"
repository: cortexso/ichigo-0.5
last_updated: 2025-08-29
license: mit
library_name:
  - pytorch
frameworks:
  - pytorch
downloads: 96
stars: 0
---

# ichigo-0.5

> ichigo-0.5 - cortexso 在 ModelScope 开源的模型。This model is a supervised fine-tuned (SFT) version of homebrewltd/Ichigo-llama3.1-s-base-v0.3, trained on over 1 billion tokens from the Instruction Speech WhisperVQ v4 dataset. This dataset builds upon Instruction…

cortexso/ichigo-0.5 是 ModelScope 魔搭社区上的机器学习模型，采用 mit 许可。

- **Repository**: cortexso/ichigo-0.5
- **License**: mit
- **Downloads**: 96
- **Stars**: 0
- **Last updated**: 2025-08-29

Source: https://www.modelscope.cn/models/cortexso/ichigo-0.5

---

## Overview

This model is a supervised fine-tuned (SFT) version of homebrewltd/Ichigo-llama3.1-s-base-v0.3, trained on over 1 billion tokens from the Instruction Speech WhisperVQ v4 dataset. This dataset builds upon Instruction Speech WhisperVQ v3, incorporating multi-turn speech conversations and advanced noise rejection capabilities.

As a result, the Ichigo-llama3s models offer enhanced robustness to noisy environmental inputs and improved handling of multi-turn conversations, ensuring greater reliability and performance in real-world applications.
## Variants

| No | Variant | Cortex CLI command |
| --- | --- | --- |
| 1 | [gguf](https://huggingface.co/cortexso/ichigo-0.5/tree/main) | `cortex run ichigo-0.5` |


## Use it with Jan (UI)

1. Install **Jan** using [Quickstart](https://jan.ai/docs/quickstart)
2. Use in Jan model Hub:
    ```text
    cortexso/ichigo-0.5
    ```
## Use it with Cortex (CLI)

1. Install **Cortex** using [Quickstart](https://cortex.jan.ai/docs/quickstart)
2. Run the model with command:
    ```bash
    cortex run ichigo-0.5
    ```
## Credits

- **Author:** HomebrewResearch
- **Converter:** [Homebrew](https://www.homebrew.ltd/)
- **Original License:** [License]()
- **Papers:** [Papers]()