Upload README.md with huggingface_hub

README.md

@@ -1,21 +1,38 @@
 ---
-base_model: unsloth/Qwen2.5-Coder-1.5B-Instruct-bnb-4bit
-tags:
-- text-generation-inference
-- transformers
-- unsloth
-- qwen2
 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
 ---
 
-# Uploaded finetuned  model
+# 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
 
-- **Developed by:** 675uj
-- **License:** apache-2.0
-- **Finetuned from model :** unsloth/Qwen2.5-Coder-1.5B-Instruct-bnb-4bit
+- **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
 
-This qwen2 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
+## License
 
-[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
+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.