for-the-small-shield-lora

Foreward

This is part of a bard model I created with a first draft of an epic fantasy adventure novel I wrote called For The Small Shield, published in GitHub: https://github.com/wordsum/For_The_Small_Shield

The size of the bard model is the smallest I was able to use to generate meaningful output, given the limited amount ot fine-tuing data I had to train the bard LLM, only 2,000 QA pairs: https://huggingface.co/datasets/wordsum/for-the-small-shield-instruct

The bard LLM is not terrible, and the stories of the bard are more historically accurate for the fantasy world when the bard is given the For The Small Shield GraphRAG of Chapters: https://huggingface.co/datasets/wordsum/for-the-small-shield-chapters

The bard is a happy mess of a song that I will revisit in a few months, with all the lessons learned from creating this bard LLM. And I will likely add bonus QA Pairs for the history of Gods and Realms from Of The Small Shield: https://www.instagram.com/ofthesmallshield

Like the original For The Small Shield, Of The Small Shield are stories in dioramas created by me and words written by me, Kalab J. Oster, unlike the words that follow.

Llama-3-for-the-small-shield — LoRA adapter (v5)

Built with Meta Llama 3

LoRA adapter for Carlos, the Barded Dwarf (Rise&Set universe). Apply it on top of the base model instead of downloading the full merged weights.

• Developed by: kalaboster (published under the wordsum organization)
• Base model: NousResearch/Hermes-2-Pro-Llama-3-8B
• Adapter type: LoRA (PEFT), r=32, α=64, dropout 0.0
• Target modules: q, k, v, o, gate, up, down projections
• Merged / GGUF versions: wordsum/for-the-small-shield
• Training data: wordsum/for-the-small-shield-instruct

Usage

from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer

base = AutoModelForCausalLM.from_pretrained(
    "NousResearch/Hermes-2-Pro-Llama-3-8B", torch_dtype="bfloat16", device_map="auto"
)
model = PeftModel.from_pretrained(base, "wordsum/for-the-small-shield-lora")
tok = AutoTokenizer.from_pretrained("wordsum/for-the-small-shield-lora")

Prompt format is ChatML (<|im_start|> / <|im_end|>); see the merged model card for the recommended system prompt and sampling settings.

Data provenance & attribution

The training data combines human-authored and AI-generated material: kalaboster wrote the first-draft novel For The Small Shield (https://github.com/wordsum/For_The_Small_Shield) and the system/character prompt; Claude (Anthropic) turned that novel into the input/output QA pairs used for training.

License

Base model is a Llama 3 derivative — the Llama 3 Community License applies to this adapter's use with the base. Confirm before publishing.

---

This adapter card was drafted by Claude (Anthropic), model claude-opus-4-8, on 2026-08-04. The adapter weights are the author's own work.