This is a LoRA adapter fine-tuned on 500,000 synthetic instruction-style samples covering quality-management systems, ISO standards, auditing, risk-based thinking, CAPA, Six Sigma, Lean, SPC, FMEA, and related topics.

Completed by Aboutknowledge (Hong Kong) Limited — Alex Lee.

License note: the LoRA weights in this repository are released under the same terms as the base model, the Llama 3.2 Community License Agreement. Please review Meta's license before using or redistributing the merged weights.

Model details

Item	Value
Base model	`unsloth/Llama-3.2-1B-Instruct`
Fine-tuning framework	Unsloth
LoRA rank (r)	16
LoRA alpha	16
LoRA dropout	0.0
Quantized training	4-bit NF4 (bnb)
Training records	500,000 (subset of a 5M synthetic dataset)
Training steps	10,000
Final train loss	0.1136
Sequence length	2048

Included files

adapter_model.safetensors / adapter_config.json — standard PEFT LoRA adapter.
quality_ollama.q8_0.gguf — Q8_0 GGUF file ready for Ollama.
Modelfile — example Ollama Modelfile (edit the FROM path after downloading).

Use with transformers / Unsloth

python

from unsloth import FastLanguageModel

model, tokenizer = FastLanguageModel.from_pretrained(
    model_name="unsloth/Llama-3.2-1B-Instruct",
    max_seq_length=2048,
    dtype=None,
    load_in_4bit=True,
)
model = FastLanguageModel.get_peft_model(model, r=16, lora_alpha=16)
model.load_adapter("alexlkc28/quality-lora-llama32-1b", adapter_name="default")

messages = [
    {"role": "system", "content": "You are an expert in quality management systems and ISO standards."},
    {"role": "user", "content": "What does ISO 9001:2015 clause 8.7 require?"},
]
inputs = tokenizer.apply_chat_template(messages, return_tensors="pt", tokenize=True).to("cuda")
outputs = model.generate(inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Use with Ollama

Download the GGUF and Modelfile from this repo.
Update the FROM line in the Modelfile to point to the downloaded GGUF path.
Create the model:

bash

ollama create quality-lora -f /path/to/Modelfile
ollama run quality-lora

Training data

The data was generated synthetically from a compact ISO/quality-management knowledge base covering:

ISO 9001, 14001, 45001, 27001, 13485, 50001
IATF 16949 (automotive), AS9100D (aerospace)
PDCA, risk-based thinking, process approach, CAPA, 8D, 5 Whys, FMEA, SPC, MSA, 5S, Lean, Six Sigma
Audit checklists, nonconformity reports, KPI suggestions, interview questions

The full 5M-record dataset is available locally in the project directory as data/quality_5m.parquet.

Limitations

Synthetic data can contain occasional grammar artifacts or mix standards in generic answers; always verify against the official standard text for compliance decisions.
This is a small 1B model; while useful for Q&A and drafting, it should not replace human auditors or regulatory review.