Qwen3-Coder-30B-A3B-Kubernetes-Instruct-LoRA

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel

# 1. Define Model IDs
base_model_id = "Qwen/Qwen3-Coder-30B-A3B-Instruct"
adapter_id = "Dogacel/Qwen3-Coder-30B-A3B-Kubernetes-Instruct-LoRA"

# 2. Load Base Model (with device_map for memory efficiency)
model = AutoModelForCausalLM.from_pretrained(
    base_model_id,
    torch_dtype=torch.float16,
    device_map="auto",
    low_cpu_mem_usage=True
)

# 3. Load the LoRA Adapter
model = PeftModel.from_pretrained(model, adapter_id)
tokenizer = AutoTokenizer.from_pretrained(base_model_id)

# 4. Run Inference
messages = [
    {"role": "system", "content": "You are a Kubernetes expert. Diagnose issues step-by-step, then provide the fixed YAML configuration."},
    {"role": "user", "content": "When I run kubectl apply, I get the following error: error validation data: [ValidationError(Deployment.spec.template.spec.containers[0]): unknown field \"imagePullPolicy\" in io.k8s.api.core.v1.Container]"}
]

text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer([text], return_tensors="pt").to(model.device)

outputs = model.generate(**inputs, max_new_tokens=2048)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))