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

Base Model: <a href="https://huggingface.co/Qwen/Qwen2.5-3B-Instruct" target="_blank" rel="noopener noreferrer" class="text-blue-400 hover:text-blue-300 underline underline-offset-2 transition-colors">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

Part of SYSBREAK - A cyberpunk terminal-based game.