ardeshir

1. Start now with QLoRA SFT on an 8B instruct modelin LLaMA-Factory or Axolotl: r=16–32, α=32, all-linear, LR 2e-4, 3 epochs,train_on_inputs:false. Dataset = (request → tool call → grounded answer). Target metric: tool-call schema-validity and solver-acceptance rate, not loss.Threshold to advance:if validity ≥ your bar, ship; if not, continue.
2. If behavior issues remain, add a LoRA DPO pass(β=0.1, LR 5e-6) on (faithful-tool-call vs fabricated) pairs. Cheap, low-risk.
3. Only if validity/acceptance still misses the bar, run a GRPO stagewith the solver as a composed verifiable reward (format + canonical-ID + solver-acceptance), in TRL (or Unsloth if single-GPU), with vLLM andloss_type="dr_grpo". Budget ≥2 GPUs and real monitoring.Change trigger:adopt GRPO when the gap between “imitatable” and “verifiable-correct” behavior is what’s blocking you.
4. Serving on Azure/AKS:use vLLM with multi-LoRA to host the merged/adapter model; the same vLLM stack doubles as GRPO’s generation backend, so standardizing on it ea

ardeshir

Agent Guidelines for Rust Code Quality

This document provides guidelines for maintaining high-quality Rust code. These rules MUST be followed by all AI coding agents and contributors.

Your Core Principles

All code you write MUST be fully optimized.

"Fully optimized" includes:

ardeshir

FROM julia:0.6

RUN apt-get update \
    && apt-get install -y \
    build-essential \
    vim \
    tmux \
    unzip \
    cmake \
    && apt-get clean

ardeshir

Lab 1, step 8
argocd app create roar-deploy-k8s --repo https://github.com/brentlaster/roar-deploy-k8s --path . --dest-server $CLUSTER_IP --dest-namespace roar

Lab 3, step 3
argocd repo add git@10.0.2.15:/git/repos/roar-k8s-helm.git --ssh-private-key-path ~/.ssh/id_rsa

Lab 4, step 9
argocd proj create jenkins-proj -d https://10.0.2.15:8443,* -s git@10.0.2.15:/git/repos/roar-min-deploy.git

Lab 4, step 11

ardeshir

name: Security audit
on:
  push:
    paths:
      - '**/Cargo.toml'
      - '**/Cargo.lock'
jobs:
  security_audit:
    runs-on: ubuntu-latest
    steps:

ardeshir

{
    "Version": "2012-10-17",
    "Statement": [
        {
            "Sid": "AllowAllUsersToListAccounts",
            "Effect": "Allow",
            "Action": [
                "iam:ListAccountAliases",
                "iam:ListUsers",
                "iam:GetAccountSummary"

ardeshir

trigger:
- devel
pool:
  vmImage: ubuntu-latest
variables:
  - group: TerraformConfiguration
  - group: TerraformVariables
parameters:
  - name: ENVIRONMENT
    default: DEV

ardeshir

trigger:
- main 
pool:
  vmImage: ubuntu-latest

variables:
  - group: TerraformConfiguration
  - group: TerraformVariables
parameters:
  - name: ENVIRONMENT 

ardeshir

#!/bin/bash

set -e

if [[ "$#" -ne 4 ]]; then
  echo "Usage: encrypt.sh <CMK_ID> <AWS_REGION> <INPUT_FILE> <OUTPUT_FILE>"
  exit
fi

CMK_ID="$1"

ardeshir

#!/usr/bin/env bash

# terraform-security1-app builds the security1 site envs

# usage execute terraform code using the "terraform-envs.sh" script. This script is invoked as follows:

# ./terraform-envs.sh dev 

# env is a reference to one of the subfolders in the env directory. 
# variable files and terraform code in these directories will be included upon the execution of the script.