README.md

---
license: apache-2.0
base_model: Qwen/Qwen2.5-3B-Instruct
tags:
- lora
- sysbreak
- event-generation
- qwen2.5
- cyberpunk
library_name: peft
---

# sysbreak-grid-runner-lora

LoRA adapter for SYSBREAK event generation (Qwen2.5-3B-Instruct base)

## Model Details

- **Base Model**: [Qwen/Qwen2.5-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-3B-Instruct)
- **Fine-tuning Method**: LoRA (Low-Rank Adaptation)
- **Model Type**: Causal Language Model
- **Language**: English
- **License**: Apache 2.0
- **Use Case**: GRID-RUNNER content generation for SYSBREAK cyberpunk game

## Usage

```python
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel

# Load base model
base_model = AutoModelForCausalLM.from_pretrained(
    "Qwen/Qwen2.5-3B-Instruct",
    device_map="auto",
    torch_dtype="auto"
)

# Load LoRA adapter
model = PeftModel.from_pretrained(base_model, "nullvektordom/sysbreak-grid-runner-lora")
tokenizer = AutoTokenizer.from_pretrained("nullvektordom/sysbreak-grid-runner-lora")

# Generate
prompt = "Generate cyberpunk content"
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=512)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
```

## Project

Part of [SYSBREAK](https://github.com/nullvektordom/sysbreak) - A cyberpunk terminal-based game.