Ttimms/bible-ai-qwen3.5-4b-lora

Bible AI Assistant — Qwen3.5-4B LoRA (SFT + ORPO)

LoRA adapter (r=16, alpha=32, targeting all attention/MLP projections) fine-tuned on Qwen/Qwen3.5-4B for a locally-hosted Bible Q&A assistant. Trained in two stages — supervised fine-tuning followed by ORPO preference alignment — over 5,925 total training steps.

Status: snapshot, not under active development right now. This is the checkpoint behind the assistant described in the bible-ai-assistant repo. The project may resume and this checkpoint may be superseded — check the GitHub repo for the current state before assuming this is the latest version.

What this is part of

This adapter is one component of a full-stack Bible Q&A system: hybrid RAG retrieval (BM25 + dense ChromaDB search + Reciprocal Rank Fusion + cross-encoder reranking), constitutional-AI guardrails, an optional voice pipeline (Faster-Whisper STT + Kokoro TTS), and a Gradio UI — 183 tests, 55% coverage, full CI/CD. See the GitHub repo for the complete system; this repo is just the model weights.

Training

Stage	Detail
SFT	~1,800 diverse examples, LoRA (Unsloth/PEFT/TRL), bf16
ORPO	500 preference pairs, preference alignment on top of the SFT adapter
Total steps	5,925
LoRA config	r=16, lora_alpha=32, lora_dropout=0.1, targets: q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj

Training run tracked in Weights & Biases (34 runs across the full project).

Usage

from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer

base = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3.5-4B", dtype="bfloat16")
model = PeftModel.from_pretrained(base, "Ttimms/bible-ai-qwen3.5-4b-lora")
tokenizer = AutoTokenizer.from_pretrained("Ttimms/bible-ai-qwen3.5-4b-lora")

The production deployment merges this adapter and exports to GGUF (F16 + Q4_K_M) for Ollama serving — see scripts/ in the GitHub repo for the merge/export pipeline.

License

MIT — matches the upstream project license.