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

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

Model Description

Qwen3-Coder-30B-A3B-Kubernetes-Instruct is a specialized fine-tune of Qwen3-Coder-30B-A3B-Instruct.

It is designed to act as an assistant for yoru Kubernetes related configuration troubleshooting, specifically optimized for YAML generation.

• —Developed by: Doğaç Eldenk, Robin Luo – Northwestern University

• —Model type: Large Language Model (Fine-tune)
• —Language(s) (NLP): English, YAML
• —License: Apache-2.0
• —Finetuned from model: Qwen/Qwen3-Coder-30B-A3B-Instruct

Model Sources

• —Repository: https://huggingface.co/Dogacel/Qwen3-Coder-30B-A3B-Kubernetes-Instruct
• —Paper: (In-progress) <!-- - Demo: -->

Uses

<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->

Direct Use

<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->

This model is designed to assist Site Reliability Engineers (SREs), DevOps professionals, and Platform Engineers. It acts as an expert assistant for:

• —Kubernetes Troubleshooting: Analyzing error logs, kubectl describe outputs, and CrashLoopBackOff scenarios.
• —YAML Generation: Writing production-ready manifests for Deployments, Services, Ingresses, StatefulSets, and NetworkPolicies.
• —Infrastructure as Code: Converting natural language requirements into valid Kubernetes configurations.
• —Architecture Q&A: Answering questions about cluster architecture, networking (CNI), and storage (CSI).

Bias, Risks, and Limitations

<!-- This section is meant to convey both technical and sociotechnical limitations. -->

• —YAML Hallucination: Like all LLMs, this model can generate syntactically correct but logically flawed YAML. Always validate generated manifests (kubectl apply --dry-run=client -f ...) before applying to production.
• —Version Bias: The model's knowledge is based on Kubernetes versions available up to the training cutoff. It may hallucinate deprecated APIs (e.g., extensions/v1beta1) or be unaware of very recent Alpha features.
• —Security Risks: The model might suggest configurations with relaxed security contexts (e.g., privileged: true) if not explicitly instructed otherwise.

Recommendations

<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->

Users should treat this model as a "Copilot" rather than an autonomous operator. All generated YAML should be reviewed by a human and scanned by static code analyzers before deployment.

How to Get Started with the Model

Use the code below to get started with the model.

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))

Training Details

Training Data

<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->

This model is fine-tuned on over 20,000 samples of Kubernetes related Q&A pairs from the community forums.

Training Procedure

<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->

Training took 2 epochs on 4 x H100 GPUs over 14 hours.

Preprocessing

All Q&A pairs are processed by another LLM (GPT 4.1-mini) to have the same formatting,

1. 1.Identification: (one sentence - what's wrong)
2. 2.Reasoning: (root cause explanation)
3. 3.Remediation: (fix approach)
4. 4.Fixed YAML configuration in ```yaml code block

Training Hyperparameters

• —Training regime: BF16 Mixed Precision (Bfloat16) <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
• —Method: QLoRA 4-Bit (Quantized Low-Rank Adaptation)
• —Rank (r): 64
• —Alpha: 32
• —Target Modules: Attention-only – ["v_proj", "q_proj", "k_proj", "o_proj"]

Evaluation

<!-- This section describes the evaluation protocols and provides the results. -->

The evaluation is run on a validation set of 100 Q&A pairs and we compared YAML similarities of the generated fixes.

Citation

<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->

BibTeX:

[TODO]