gordon-ramsay-code-auditor

Autonomous fine-tuned model artifact synthesized via JESUS Sovereign Cloud Model Forge (hf-colab-forge).

Model Details

• Base Model: Qwen/Qwen2.5-Coder-1.5B-Instruct
• Artifact Type: LoRA Adapter Weights
• Fine-Tuning Method: QLoRA (NF4 4-bit / Double Quantization)
• Execution Grid: Google Colab GPU (Cloud Accelerator (NVIDIA) )
• Creation Date: 2026-08-30 02:53:43 UTC

Training Hyperparameters & Telemetry

Parameter	Value
Base Model	Qwen/Qwen2.5-Coder-1.5B-Instruct
LoRA Rank ($r$)	N/A
LoRA Alpha ($\alpha$)	N/A
Epochs	N/A
Batch Size	N/A (Gradient Accum: 4)
Learning Rate	N/A
Final Loss	N/A
Training Duration	N/As

Quickstart & Inference

Python (transformers + peft)

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

base_model_id = "Qwen/Qwen2.5-Coder-1.5B-Instruct"
adapter_id = "dcmutlu/gordon-ramsay-code-auditor"

tokenizer = AutoTokenizer.from_pretrained(base_model_id)
base_model = AutoModelForCausalLM.from_pretrained(
    base_model_id,
    torch_dtype=torch.float16,
    device_map="auto"
)
model = PeftModel.from_pretrained(base_model, adapter_id)

prompt = "Triage user intent to the sovereign tool mesh."
inputs = tokenizer(prompt, return_tensors="pt").to("cuda" if torch.cuda.is_available() else "cpu")
outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Apple Silicon / Host Deployment (llama.cpp / GGUF)

If utilizing GGUF weights on macOS (M-Series Metal acceleration):

# Run via llama.cpp
llama-cli -m gordon-ramsay-code-auditor-Q4_K_M.gguf -p "Triage user intent:" -ngl 99 -c 2048