Downloads · 30 days
10
21% of all-time downloads
xile42/qwen36-27b-lord-of-mysteries-lora
qwen36-27b-lord-of-mysteries-lora is a text generation model from xile42. Use it when you need the model to write or continue text. It is set up for peft. The card lists the license as other.
This repository provides a PEFT LoRA adapter for Qwen/Qwen3.6-27B, trained for source-grounded question answering over a curated Lord of the Mysteries knowledge base.
Downloads · 30 days
10
21% of all-time downloads
All-time downloads
48
Public
Repo size
179 MB
Likes
0
Public
Click a slice to open those files.
.safetensors159 MB · 89%
From the Hugging Face model README
This repository provides a PEFT LoRA adapter for Qwen/Qwen3.6-27B, trained for source-grounded question answering over a curated Lord of the Mysteries knowledge base.
The recommended workflow pairs this adapter with the companion evidence dataset and retrieval script. The retrieval layer selects a relevant source page or fact card first, then the adapter is used to produce a concise answer with source attribution.
This is an auditable first release for research and personal knowledge-base experiments. It is not an official encyclopedia and should not be treated as a complete standalone memory model.
xile42/qwen36-27b-lord-of-mysteries-loraQwen/Qwen3.6-27Bxile42/lord-of-mysteries-fandom-evidence-sftThis adapter is intended for:
For best results, use the adapter with the companion dataset files:
fandom_lotm_pages.jsonlretrieval_aliases.jsoncurated_lotm_facts.jsoninference_example.pyThe adapter was trained on evidence-aware chat examples derived from 425 Lord of the Mysteries Fandom Wiki pages. The dataset preserves source URLs and revision metadata in the source records, while the runtime attaches exact source URLs programmatically during retrieval.
The dataset is not built from raw novel chapters and must not be used to reconstruct, redistribute, or replace the original novel text.
The current release was evaluated with retrieval and source-attribution checks:
| Check | Result |
|---|---|
| Fixed RAG evaluation | 12/12 |
| Broad source retrieval evaluation | 49/49 |
| Missing-evidence abstention | Passed |
| Source URL fidelity | Attached by retrieval runtime |
These checks measure retrieval and source-grounded behavior. They do not prove that the adapter has memorized every character, event, or chapter-level detail without external evidence.
Install dependencies and download the companion dataset:
pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu128
pip install huggingface_hub
hf download xile42/lord-of-mysteries-fandom-evidence-sft --repo-type dataset --local-dir lord-of-mysteries-fandom-evidence-sft
cd lord-of-mysteries-fandom-evidence-sft
pip install -r requirements-inference.txt
Run a retrieval-only check:
python inference_example.py --retrieval-only --question "What is the source URL for Tarot Club?"
python inference_example.py --retrieval-only --questions-file demo_questions.jsonl
Run generation with the LoRA adapter:
python inference_example.py \
--adapter xile42/qwen36-27b-lord-of-mysteries-lora \
--question "Introduce Tarot Club from Lord of the Mysteries and include the source."
Raw adapter loading:
import torch
from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig
base = "Qwen/Qwen3.6-27B"
adapter = "xile42/qwen36-27b-lord-of-mysteries-lora"
quantization_config = BitsAndBytesConfig(
load_in_4bit=True,
bnb_4bit_quant_type="nf4",
bnb_4bit_use_double_quant=True,
bnb_4bit_compute_dtype=torch.bfloat16,
)
tokenizer = AutoTokenizer.from_pretrained(base, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
base,
quantization_config=quantization_config,
device_map="auto",
torch_dtype=torch.bfloat16,
trust_remote_code=True,
)
model = PeftModel.from_pretrained(model, adapter)
This adapter is subject to the license terms of Qwen/Qwen3.6-27B and the rights of the training data. The companion dataset is derived from Fandom Wiki content, which is generally available under CC BY-SA 3.0 unless otherwise noted on the source page. Review the source attribution inventory before making a public release.