Instructions to use frostedunicorn/logos-v61-sft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use frostedunicorn/logos-v61-sft with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="frostedunicorn/logos-v61-sft")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("frostedunicorn/logos-v61-sft")
model = AutoModelForCausalLM.from_pretrained("frostedunicorn/logos-v61-sft", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use frostedunicorn/logos-v61-sft with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "frostedunicorn/logos-v61-sft"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "frostedunicorn/logos-v61-sft",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/frostedunicorn/logos-v61-sft

SGLang

How to use frostedunicorn/logos-v61-sft with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "frostedunicorn/logos-v61-sft" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "frostedunicorn/logos-v61-sft",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "frostedunicorn/logos-v61-sft" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "frostedunicorn/logos-v61-sft",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use frostedunicorn/logos-v61-sft with Docker Model Runner:
```
docker model run hf.co/frostedunicorn/logos-v61-sft
```

Logos v6.1-SFT — Abrahamic Religious Texts Model (Research Alpha)

RESEARCH USE ONLY — This model has known limitations. Not suitable for religious advice, fatwa generation, or authoritative scriptural interpretation.

Overview

Logos v6.1-SFT is a research-grade language model specialized in Abrahamic religious texts across Arabic, Hebrew, Greek, English, Latin, fine-tuned from Qwen2.5-7B-Instruct using QLoRA (r=32, alpha=64).

This version includes:

Base LM training: 3 epochs on 130K verses (multilingual corpus)
SFT training: 30K instruction-tuned Q&A samples
Citation SFT: Additional 1 epoch on 8.2K citation-format examples (experimental)

Model Details

Field	Value
Base	Qwen/Qwen2.5-7B-Instruct
Architecture	Qwen2ForCausalLM
Training	QLoRA 4-bit, r=32, alpha=64, dropout=0.1
Merged	Yes (all LoRA adapters merged into base)
Dtype	float16
Params	~7.6B
Context	32K tokens (base GGUF metadata)

Training Data

Base Corpus (130K verses)

Source	Count	Notes
Quran (Uthmani Arabic)	6,050	Public domain
Hebrew Bible (WLC)	18,155	Public domain
Septuagint (LXX)	29,107	Public domain
Talmud Bavli	10,919	Rodkinson 1918 / Sefaria
Hadith (Bukhari, Muslim, Abu Dawud, Tirmidhi, Ibn Majah, Nasai)	~63K	English translations
Tafsir (Ibn Kathir, Siraj, Jalalayn)	~16K	Exegesis commentary
Mishnah	4,192	Rodkinson 1918 (PD)
Vulgate	35,809	Public domain

SFT Dataset (30K samples)

Instruction-tuned Q&A pairs covering verse recall, cross-tradition comparison, citation lookup, tafsir explanation, and multilingual text understanding.

Citation SFT Dataset (8.2K samples)

Citation formatting examples for Quran (Surah X:Y), Bible (Book Chapter:Verse), and Talmud (tractate page) formats.

Evaluation (v6.1-SFT, seed=42, greedy)

Category	Score	Notes
Overall Mean	0.506	Research alpha
Cross-Tradition Knowledge	0.817	Moses/Paul/Quran facts
Arabic Grammaticality	1.000	Case-ending detection
Arabic Classical Fluency	1.000	Arabic char ratio
Arabic Diacritic F1	0.679	Tashkeel accuracy
Hallucination Detection	0.500	Trap questions
Talmudic Reference	0.410	Tractate + page lookup
Citation Accuracy	0.200	Surah:ayah, book:chapter:verse
Verse Recall (exact)	0.000	Relies on RAG, not memorization
Tafsir Overlap	0.005	Commentary overlap

Known Limitations

Low citation accuracy (20%) — inconsistent surah:ayah and book:chapter:verse formatting
Zero exact verse recall — model has not memorized verse text; relies on RAG for verbatim quotes
Hallucination rate 50% — too high for production factual queries
Tafsir not learned — needs DPO or targeted tafsir training
Arabic diacritics — decent F1 but not scholarly-grade tashkeel
Research only — not intended for religious advice or authoritative interpretation

Usage

Transformers (GPU)

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

model = AutoModelForCausalLM.from_pretrained(
    "frostedunicorn/logos-v61-sft",
    torch_dtype=torch.float16,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("frostedunicorn/logos-v61-sft")

prompt = "Explanation of Surah 1:1 in the Quran:"
messages = [{"role": "user", "content": prompt}]
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(text, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))

Ollama

ollama create logos-v61-sft -f Modelfile
ollama run logos-v61-sft "What is the first surah of the Quran?"

Chat Template

{{ if .System }}<|im_start|>system
{{ .System }}<|im_end|>{{ end }}{{ if .Prompt }}<|im_start|>user
{{ .Prompt }}<|im_end|>
<|im_start|>assistant
{{ end }}{{ .Response }}<|im_end|>

System Prompt

You are Logos, an AI assistant specialized in Abrahamic religious texts across Hebrew, Greek, Arabic, English, and Latin. You provide accurate citations from Torah, Bible, Quran, and related sources. You handle sacred texts with reverence and never mix registers inappropriately. When you don't know something, you say so.

License & Attribution

Model weights: Apache 2.0 (research use)

Upstream data licenses:

Quran: Public Domain
WLC Hebrew Bible: Public Domain
Septuagint (LXX): Public Domain
Talmud/Mishnah (Rodkinson): Public Domain
Hadith English translations: Various (CC-BY, CC-BY-SA)
Sefaria texts: CC-BY / CC-BY-SA (requires attribution)
Gutenberg texts: Public Domain

Citation

@misc{logos2026,
  title={Logos v6.1-SFT: Abrahamic Religious Texts Model},
  author={dtfrost5},
  year={2026},
  publisher={Hugging Face},
  howpublished={\url{https://huggingface.co/frostedunicorn/logos-v61-sft}}
}

Evaluated 2026-09-17. Training loss: 0.421, combined SFT + citation LoRA merged.

Downloads last month: 236

Safetensors

Model size

8B params

Tensor type

F16

Model tree for frostedunicorn/logos-v61-sft

Base model

Qwen/Qwen2.5-7B

Finetuned

Qwen/Qwen2.5-7B-Instruct

Finetuned

(3106)

this model