Downloads · 30 days
11
19% of all-time downloads
sreenathvemula/christian-qwen3-32b-lora-r32
christian-qwen3-32b-lora-r32 is a text generation model from sreenathvemula. Use it when you need the model to write or continue text. It is set up for peft. The card lists the license as apache-2.0.
A fine-tuned Qwen3-32B that answers Bible-study questions from within historic Nicene-Chalcedonian Protestant orthodoxy, and looks up Scripture, commentary, lexicons and the confessions before it answers rather than r…
Downloads · 30 days
11
19% of all-time downloads
All-time downloads
57
Public
Repo size
1.1 GB
Likes
0
Public
Click a slice to open those files.
.safetensors1.1 GB · 100%
From the Hugging Face model README
A fine-tuned Qwen3-32B that answers Bible-study questions from within historic Nicene-Chalcedonian Protestant orthodoxy, and looks up Scripture, commentary, lexicons and the confessions before it answers rather than reciting from memory.
Two independent pieces. Use either on its own.
| what it is | where | |
|---|---|---|
| The model | rank-32 LoRA over Qwen/Qwen3-32B | sreenathvemula/christian-qwen3-32b-lora-r32 |
| The tools | live MCP server, 10 study tools, free, no key | https://sreenathvemula-christianmcp.hf.space/gradio_api/mcp/sse |
It looks things up. Ask about Romans 8:28 and it calls passage → commentary →
cross_references, then answers from what came back — 23 classic commentators (Calvin, Gill,
Henry, Poole, Keil-Delitzsch, Robertson, Lightfoot…), the Treasury of Scripture Knowledge,
Strong's/Thayer's/BDB/LSJ, Nave's and Torrey's topical Bibles, ISBE and McClintock &
Strong's, and 17 creeds and confessions.
It holds a position. Doctrine is stated as settled and true, not hedged into "some believe / others believe."
It refuses what it should refuse. It does not pronounce on anyone's eternal state, does not speak in God's voice, does not compose prayers for you, and does not claim to feel or believe anything itself. Asked "My mother died last week, she never believed, is she in hell?" it answers: "No, and that is not a dodge — it is the only honest answer, because it is not yours to know."
| stage | data | detail |
|---|---|---|
| SFT | 128,429 examples | QLoRA r=16, tool-calling traces + doctrine + pastoral answers |
| DPO | 2,792 preference pairs | r=16, β=0.1, lr 5e-6, 333 steps — eval accuracy 0.992 |
Both stages combined into one rank-32 LoRA by exact concatenation (max relative error 5.4e-16 — not an approximation). Held-out test set of 23,554 examples was never trained on.
vllm serve Qwen/Qwen3-32B \
--enable-lora --max-lora-rank 32 \
--lora-modules christian-qwen3-32b=sreenathvemula/christian-qwen3-32b-lora-r32 \
--max-model-len 16384 --enable-prefix-caching \
--reasoning-parser qwen3 \
--enable-auto-tool-choice --tool-call-parser hermes
Needs ~80 GB VRAM in bf16. A 4-bit quantisation fits ~19 GB.
pip install -r requirements.txt
OPENAI_BASE_URL=http://localhost:8000/v1 python app.py
Open http://localhost:7860.
Any OpenAI-compatible endpoint works — set OPENAI_BASE_URL to Modal, RunPod, Featherless,
llama.cpp server, or your own box. No code changes.
The MCP server is public and free. In Claude Desktop or any MCP client:
{
"mcpServers": {
"christian": {
"url": "https://sreenathvemula-christianmcp.hf.space/gradio_api/mcp/sse"
}
}
}
1. Thinking must be ON. With enable_thinking=false the model stops calling tools
entirely and answers from memory — inventing commentator attributions like "Robertson notes
the Greek…". Measured on identical prompts: thinking on → 3 correct lookups; thinking off →
zero lookups and a fabricated citation. This is the single most important setting.
2. Never use greedy decoding. It causes degeneration loops (measured: one phrase repeated 78 times). Use:
{"temperature": 0.6, "top_p": 0.95, "top_k": 20, "repetition_penalty": 1.03}
Keep repetition_penalty ≤ 1.05 — higher punishes the model for legitimately repeating words
inside a quoted verse.
3. Send the bundled tools_schema.json, not an auto-generated one. This is the schema
the model was trained against. A schema without required arrays and with verbose
descriptions produced zero tool calls; this one produces the trained
passage → commentary → cross_references pattern. tools_mcp.py loads it for you.
Bundled defaults already correct: 5 lookups per question, max 2 commentary, max 2 per tool, duplicate-call suppression, and all 10 schemas sent in a fixed order (which keeps the prompt prefix stable so vLLM's prefix cache hits).
| file | role |
|---|---|
app.py | Gradio chat UI |
agent.py | ReAct loop, tool budget, <think> stripping |
tools_mcp.py | MCP client; maps bare tool names to the hosted server |
tools_schema.json | the schema the model was trained on — do not replace |
CANONICAL.txt | the serving system prompt |
A 32B on a dedicated GPU is expensive for sparse traffic — you rent the whole card whether one person or twenty are asking. Roughly, at current rates: ~$0.69/hr on a 24 GB card with a 4-bit quantisation, ~$2.50/hr on an 80 GB card in bf16. Flat-rate hosts and HF Spaces ZeroGPU (where quota is charged to each visitor rather than the host) are cheaper ways to open it to a congregation.