Instructions to use krush420/qwen3-coder-30b-sre-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use krush420/qwen3-coder-30b-sre-lora with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-Coder-30B-A3B-Instruct")
model = PeftModel.from_pretrained(base_model, "krush420/qwen3-coder-30b-sre-lora")

Transformers

How to use krush420/qwen3-coder-30b-sre-lora with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="krush420/qwen3-coder-30b-sre-lora")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("krush420/qwen3-coder-30b-sre-lora", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use krush420/qwen3-coder-30b-sre-lora with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "krush420/qwen3-coder-30b-sre-lora"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "krush420/qwen3-coder-30b-sre-lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/krush420/qwen3-coder-30b-sre-lora

SGLang

How to use krush420/qwen3-coder-30b-sre-lora with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "krush420/qwen3-coder-30b-sre-lora" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "krush420/qwen3-coder-30b-sre-lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "krush420/qwen3-coder-30b-sre-lora" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "krush420/qwen3-coder-30b-sre-lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use krush420/qwen3-coder-30b-sre-lora with Docker Model Runner:
```
docker model run hf.co/krush420/qwen3-coder-30b-sre-lora
```

Qwen3-Coder-30B-A3B — KruschStack Sovereign Code Auditor & Remediator LoRA (`L2` Student)

Trained Through KruschStack to Benefit KruschStack

This adapter is the official L2 Local MoE Student for KruschStack (krusch-stack) — the Unified 7-Pillar, 39-Tool Model Context Protocol (MCP) & Agentic Coding Stack (npx krusch-stack init). It was distilled from trajectories generated, AST-grounded, and unit-test verified inside the KruschStack 3-Tier MCP harness so that a fast local 30B MoE model (3B active parameters) can perform Principal-level 11-phase code audits and test-gated bug remediations across the KruschStack ecosystem.

🔗 The KruschStack & Jean SRE Ecosystem

🛠️ KruschStack (7-Pillar 39-Tool MCP Stack): github.com/kruschdev/krusch-stack (npx krusch-stack init)
🤖 Jean SRE by Kruschdev (24/7 Autonomous Auditor & Distillation Harness): github.com/kruschdev/Jean-SRE-by-kruschdev
📊 Training Dataset (17,899 Trajectories): krush420/sovereign-code-audit-sft
🧠 Companion 120B Teacher QLoRA (L2.5 Burst Tier): krush420/gpt-oss-120b-sre-lora (for openai/gpt-oss-120b)

🏗️ Built With & For the KruschStack 7-Pillar Architecture

qwen3-coder-30b-sre-lora is trained specifically to reason over tool outputs from the KruschStack Unified MCP Gateway and act as the L2 Local MoE Specialist in krusch-cascade-router:

┌────────────────────────────────────────────────────────────────────────────┐
│                        KRUSCH-STACK UNIFIED GATEWAY                        │
│               `npx krusch-stack mcp`  (39 Annotated MCP Tools)             │
├──────────────────────┬───────────────────────────┬─────────────────────────┤
│ 1. WORKING MEMORY    │ 2A. CODEBASE AST & GIT    │ 2B. OS PAGE MEMORY      │
│ krusch-context-mcp   │ krusch-git                │ krusch-fs               │
│ • retrieve / remember│ • search_symbols          │ • locate / search       │
│ • revise / nudge     │ • dependency_graph        │ • page_tree / read_page │
│ • INV-12 span drift  │ • read_tree / read_blob   │ • remember_on_page      │
├──────────────────────┼───────────────────────────┼─────────────────────────┤
│ 3. 2PC HARNESS       │ 4. FRONTEND DESIGN MCP    │ 5. WORKSPACE HUB        │
│ krusch-harness       │ krusch-frontend-mcp       │ g-krusch                │
│ • run (stages diff)  │ • generate_color_palette  │ • get_agent_steering    │
│ • apply_diff (2PC)   │ • css_to_tailwind         │ • search_drive_rag      │
│ • explain / reject   │ • canonical_templates     │ • write (.gdoc/.slides) │
├──────────────────────┴───────────────────────────┴─────────────────────────┤
│ 6. COGNITIVE CASCADE ROUTER (`krusch-cascade-router`)                      │
│ • <25µs L1 fast-path -> [L2: qwen3-coder-30b-sre-lora] -> L2.5 120B        │
└────────────────────────────────────────────────────────────────────────────┘

What This Adapter Learned Through KruschStack

Gemini 4 Argon (gemini-4-argon) Golden Remediations (argon_golden_remediations): Multi-file root-cause bug fixes staged through krusch-harness and verified against live unit test suites (node:test / pytest, exit code 0).
openai/gpt-oss-120b Elitist Code Audit Trajectories (elitist_120b_teacher): 11-phase AST-grounded codebase audits using krusch-git (search_symbols, dependency_graph, read_blob) with verbatim file:startLine-endLine citations, false-positive refutation (NOT FLAGGED), and Zero-Finding convergence (CLEAN_PASS).
Zero-Leak Portability Gate: Scrubbed of all private IPs, internal hostnames, user paths, and credentials so the adapter generalizes cleanly to any local or enterprise repository using krusch-stack.

⚡ Quickstart

1. Install KruschStack (`npx krusch-stack`)

# Auto-configure Claude Code (.mcp.json), Cursor, Windsurf & Antigravity + initialize SQLite
npx krusch-stack init

# Verify all 7 stack pillars (39 annotated MCP tools)
npx krusch-stack doctor

2. Run Locally with Ollama (`Modelfile` Included)

git clone https://huggingface.co/krush420/qwen3-coder-30b-sre-lora
cd qwen3-coder-30b-sre-lora
ollama create qwen3-coder-30b-sre:latest -f Modelfile
ollama run qwen3-coder-30b-sre:latest

3. Transformers + PEFT

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

base_id = "Qwen/Qwen3-Coder-30B-A3B-Instruct"
adapter_id = "krush420/qwen3-coder-30b-sre-lora"

tokenizer = AutoTokenizer.from_pretrained(base_id)
base_model = AutoModelForCausalLM.from_pretrained(
    base_id,
    dtype=torch.bfloat16,
    device_map="auto",
)
model = PeftModel.from_pretrained(base_model, adapter_id)

4. vLLM Multi-LoRA Serving

vllm serve Qwen/Qwen3-Coder-30B-A3B-Instruct \
  --enable-lora \
  --lora-modules code-auditor=krush420/qwen3-coder-30b-sre-lora

🔬 Training Hyperparameters & Environment

Hardware: NVIDIA RTX PRO 6000 Blackwell Server Edition (96 GB VRAM, sm_120)
Base Model: Qwen/Qwen3-Coder-30B-A3B-Instruct (4-bit NF4 attention + BF16 3D MoE experts)
LoRA Config: r=16, lora_alpha=32, lora_dropout=0.05, target_modules=["q_proj", "k_proj", "v_proj", "o_proj"] (25,165,824 trainable parameters)
Training Metrics: Loss converged 0.731 $\rightarrow$ 0.214; token accuracy reached 93.36% (eval_loss=0.3358, eval_mean_token_accuracy=90.35%)
Optimizer: paged_adamw_8bit, cosine LR schedule (lr=2e-4, warmup_ratio=0.05)
Frameworks: peft 0.21.2, trl 1.16.0, transformers 5.20.2, torch 2.11.0+cu130

Downloads last month: -

Model tree for krush420/qwen3-coder-30b-sre-lora

Base model

Qwen/Qwen3-Coder-30B-A3B-Instruct

Adapter

(63)

this model

krush420
/

qwen3-coder-30b-sre-lora

Qwen3-Coder-30B-A3B — KruschStack Sovereign Code Auditor & Remediator LoRA (`L2` Student)

🔗 The KruschStack & Jean SRE Ecosystem

🏗️ Built With & For the KruschStack 7-Pillar Architecture

What This Adapter Learned Through KruschStack

⚡ Quickstart

1. Install KruschStack (`npx krusch-stack`)

2. Run Locally with Ollama (`Modelfile` Included)

3. Transformers + PEFT

4. vLLM Multi-LoRA Serving

🔬 Training Hyperparameters & Environment

Model tree for krush420/qwen3-coder-30b-sre-lora

Dataset used to train krush420/qwen3-coder-30b-sre-lora

Qwen3-Coder-30B-A3B — KruschStack Sovereign Code Auditor & Remediator LoRA (L2 Student)

🔗 The KruschStack & Jean SRE Ecosystem

🏗️ Built With & For the KruschStack 7-Pillar Architecture

What This Adapter Learned Through KruschStack

⚡ Quickstart

1. Install KruschStack (npx krusch-stack)

2. Run Locally with Ollama (Modelfile Included)

3. Transformers + PEFT

4. vLLM Multi-LoRA Serving

🔬 Training Hyperparameters & Environment

Model tree for krush420/qwen3-coder-30b-sre-lora

Dataset used to train krush420/qwen3-coder-30b-sre-lora

Qwen3-Coder-30B-A3B — KruschStack Sovereign Code Auditor & Remediator LoRA (`L2` Student)

1. Install KruschStack (`npx krusch-stack`)

2. Run Locally with Ollama (`Modelfile` Included)