dkubeio

DKube-instruct-v2-0.5B

README

License: apache-2.0

Training

Data: 1270 train / 69 held-out chat examples. 2 epochs, learning rate 0.0001, LoRA r=16 / α=32 on all attention and MLP projections. Loss is on assistant tokens only; bf16 on an NVIDIA GB10 (DGX Spark).
How the examples were made: Kubernetes troubleshooting sources covering 47 error classes were collected and chunked, and a local teacher model (mostly gpt-oss:20b, some Qwen3-8B) wrote 1–3 grounded examples per chunk. Every example was checked (real kubectl subcommands, parseable YAML, no near-duplicates) and each error class was capped at 5% of the set.

Table with columns: Source, License, Use
Source	License	Use
kubernetes.io debug and task docs (English)	CC BY 4.0	grounding for generated examples
Stack Overflow / Server Fault Q&A	CC BY-SA 4.0	grounding for generated examples
Scoutflo SRE Playbooks (K8s)	MIT	grounding for generated examples
kubernetes/* GitHub issue threads	GitHub ToS	grounding only, paraphrased
Vendor troubleshooting guides	proprietary	grounding only, paraphrased — no text copied
`jalpan04/devops-sft-dataset` (Kubernetes questions only)	Apache-2.0	direct rows
`spacezenmasterr/k8s-sft-cmd-en`	MIT	direct rows

v1's AnveshGummala/k8s-troubleshooting-customdsv3 is not used: its license is undeclared. Research-paper Q&A rows that v1's source mixed into its "Kubernetes" rows were removed.

Evaluation

Two measures, run on 2026-09-25 with the same code for every model:

Rubric ↑: over 40 canonical scenarios, the share of required root-cause and fix keywords each answer contains. It is coarse. It rewards naming the right things, not being right, so read it next to Known failures.
Loss ↓: loss on held-out assistant tokens, both on new-style examples and on v1-style rows.

Table with columns: model, rubric ↑, loss, new data ↓, loss, v1-style ↓
model	rubric ↑	loss, new data ↓	loss, v1-style ↓
Qwen2.5-0.5B-Instruct (no adapter)	0.487	1.581	2.082
t4tarzan/DKube-instruct (v1, 0.5B)	0.367	1.689	1.664
DKube-instruct-v2-0.5B (this model)	0.562	1.173	1.593
Qwen2.5-1.5B-Instruct (no adapter)	0.608	1.332	2.072

Known failures

Read from this model's own answers to the canonical scenarios:

Exit code 137: does not identify it as SIGKILL / OOMKilled; blames "startup failures, missing dependencies".
ImagePullBackOff with 401 Unauthorized: looks for tokens in kube-system and the kubeconfig instead of a docker-registry secret referenced in imagePullSecrets.
RBAC Forbidden: says to create a Role, but checks permissions with kubectl get svc and looks for API-server errors in the kubelet log.
It scores zero on the exit codes 126 / 127 / 139 / 143 and exec format error, DNS resolution, stuck Terminating pods and namespaces, and localhost:8080 refused. It can invent commands and resource types (e.g. kubectl get envvar).
Scored well: CreateContainerConfigError (ConfigMap / Secret), node affinity, PVC pending, FailedMount, Evicted, liveness / readiness probes, ProgressDeadlineExceeded, x509 errors, ResourceQuota, Docker Hub rate limits.

Usage

python

from peft import PeftModelfrom transformers import AutoModelForCausalLM, AutoTokenizer base = "Qwen/Qwen2.5-0.5B-Instruct"tok = AutoTokenizer.from_pretrained(base)model = AutoModelForCausalLM.from_pretrained(base, torch_dtype="auto")model = PeftModel.from_pretrained(model, "dkubeio/DKube-instruct-v2-0.5B") msgs = [    {"role": "system", "content": "You are DKube-instruct, a Kubernetes troubleshooting assistant. Diagnose the root cause, give exact kubectl commands or YAML fixes, and say how to verify."},    {"role": "user", "content": "Pod is CrashLoopBackOff with exit code 137. How do I fix it?"},]ids = tok.apply_chat_template(msgs, add_generation_prompt=True, return_tensors="pt")print(tok.decode(model.generate(ids, max_new_tokens=400)[0][ids.shape[1]:], skip_special_tokens=True))

The system prompt above is the one the model was trained with; answers are best with it.

License

The adapter is released under Apache-2.0. Use of the base model follows its own license (Qwen/Qwen2.5-0.5B-Instruct: Apache-2.0).

Available on FriendliAI

Dedicated Endpoints

Run this model inference on single tenant GPU with unmatched speed and reliability at scale.

Learn more

Container

Run this model inference with full control and performance in your environment.

Learn more

Model Details

Model Provider

dkubeio

Model Tree

Base

Qwen/Qwen2.5-0.5B-Instruct

Adapter

this model

Input Modalities

Text

Output Modalities