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

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

# Path to your merged model (no base model needed)
model_id = "Dogacel/Qwen3-Coder-30B-A3B-Kubernetes-Instruct"

# 1. Load the Full Model
# Use device_map="auto" to handle the 30B size efficiently
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.float16,
    device_map="auto",
    low_cpu_mem_usage=True
)

tokenizer = AutoTokenizer.from_pretrained(model_id)

# 2. 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": "My Pod is in Pending state and describing it says 'Insufficient cpu'. How do I fix this?"}
]

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))