README.md

---
license: apache-2.0
base_model: openai/gpt-oss-20b
tags:
- merge-conflicts
- git-automation
- developer-tools
- code-generation
- version-control
- devops
languages:
- en
pipeline_tag: text-generation
library_name: transformers
datasets:
- SoarAILabs/merge-conflict-dataset
metrics:
- name: exact_match
  type: exact_match
  value: 22.0
- name: token_f1
  type: f1
  value: 0.617
- name: bleu
  type: bleu
  value: 50.82
- name: rouge-l
  type: rouge
  value: 58.64
- name: levenshtein_sim
  type: similarity
  value: 0.549
- name: char_similarity
  type: similarity
  value: 0.765
  
model-index:
- name: KiteResolve-20B
  results:
  - task:
      type: text-generation
      name: Merge Conflict Resolution
    metrics:
    - name: Exact Match
      type: exact_match
      value: 22.0
    - name: Token F1
      type: f1
      value: 0.617
    - name: BLEU
      type: bleu
      value: 50.82
    - name: ROUGE-L
      type: rouge
      value: 58.64
    - name: Levenshtein Similarity
      type: similarity
      value: 0.549
    - name: Character Similarity
      type: similarity
      value: 0.765
---

# 🪁 KiteResolve-20B: AI-Powered Merge Conflict Resolution

*Developed by [Soar AI Labs](https://huggingface.co/SoarAILabs)*

<div align="center">
  <img src="https://img.shields.io/badge/License-Apache%202.0-blue.svg" alt="License">
  <img src="https://img.shields.io/badge/Model-20B%20Parameters-red.svg" alt="Parameters">
  <img src="https://img.shields.io/badge/Task-Code%20Generation-green.svg" alt="Task">
  <img src="https://img.shields.io/badge/BLEU-54.83-orange.svg" alt="BLEU Score">
</div>

## 🚀 Model Description

**KiteResolve-20B** is a fine-tuned version of GPT-OSS-20B specifically engineered for **automated Git merge conflict resolution**. This model transforms the tedious process of manually resolving merge conflicts into an intelligent, automated workflow that understands code semantics across multiple programming languages.

### ✨ Key Features

- 🎯 **20% Exact Match Accuracy** on real-world merge conflicts  
- 📈 **12% Token-F1 Score Improvement** over base model  
- 🌐 **Multi-Language Support**: Java, JavaScript, Python, C#, TypeScript, and more  
- ⚡ **Fast Inference**: Optimized for CLI and webhook integrations  
- 🔧 **Production Ready**: Designed for enterprise Git workflows  

## 📊 Performance Metrics
| Model               | Exact Match | Token F1  | BLEU      | ROUGE-L   | Char Sim  |
| ------------------- | ----------- | --------- | --------- | --------- | --------- |
| **codellama:13b**   | 0.00        | 0.193     | 13.28     | 0.208     | 0.710     |
| **llama3.1:8b**     | 0.04        | 0.583     | 50.59     | 0.610     | 0.818     |
| **gpt-oss:20b**     | **0.24**    | 0.549     | 47.19     | 0.572     | 0.736     |
| **KiteResolve-20B** | 0.22        | **0.617** | **50.82** | **0.586** | **0.765** |

*Evaluated on 50 held-out samples from real-world merge conflicts.*

## 🛠️ Usage

### Quick Start

```python
from transformers import AutoModelForCausalLM, AutoTokenizer
from unsloth.chat_templates import get_chat_template

# Load the model
model = AutoModelForCausalLM.from_pretrained("SoarAILabs/KiteResolve-20B")
tokenizer = AutoTokenizer.from_pretrained("SoarAILabs/KiteResolve-20B")
tokenizer = get_chat_template(tokenizer, chat_template="gpt-oss")

# Resolve a merge conflict
conflict = """
<<<<<<< ours
function calculateTotal(items) {
    return items.reduce((sum, item) => sum + item.price, 0);
}
=======
function calculateTotal(items) {
    return items.map(item => item.price).reduce((a, b) => a + b, 0);
}
>>>>>>> theirs
"""

messages = [{"role": "user", "content": f"Resolve this merge conflict:\n```{conflict}```"}]
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)

inputs = tokenizer([prompt], return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=200, do_sample=False)

resolution = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(resolution)
```

### Ollama 🦙️
```bash
ollama run hf.co/SoarAILabs/KiteResolve-20B/model-q4_k_m.gguf
```