| license: apache-2.0 | |
| base_model: Qwen/Qwen2.5-Coder-1.5B-Instruct | |
| datasets: | |
| - ise-uiuc/Magicoder-OSS-Instruct-75K | |
| language: | |
| - en | |
| - pl | |
| tags: | |
| - code | |
| - qwen2 | |
| - unsloth | |
| pipeline_tag: text-generation | |
| # Kyllix-Coder | |
| **Kyllix-Coder** is an AI coding assistant created by **Kyllix**. | |
| It writes, explains, reviews and debugs code in many programming languages. | |
| ## Usage with Ollama | |
| ```bash | |
| ollama run hf.co/675uj/Kyllix-Coder-GGUF:Q4_K_M | |
| ``` | |
| ## Model details | |
| - **Base model:** [Qwen/Qwen2.5-Coder-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-1.5B-Instruct) by Alibaba Cloud | |
| - **Fine-tuning:** LoRA (r=16) with [Unsloth](https://github.com/unslothai/unsloth), 600 steps | |
| - **Training data:** 10000 examples from [ise-uiuc/Magicoder-OSS-Instruct-75K](https://huggingface.co/datasets/ise-uiuc/Magicoder-OSS-Instruct-75K) plus identity examples | |
| - **Parameters:** ~1.5B | |
| - **Context length used in training:** 2048 tokens | |
| ## License | |
| Released under the [Apache 2.0 license](https://www.apache.org/licenses/LICENSE-2.0), the same license as the base model. | |
| This model is a derivative of Qwen2.5-Coder-1.5B-Instruct, Copyright (c) Alibaba Cloud. | |