Instructions to use deltakitsune/properly with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use deltakitsune/properly with Transformers:

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

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

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("deltakitsune/properly", dtype="auto")

llama-cpp-python

How to use deltakitsune/properly with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="deltakitsune/properly",
	filename="exports/gguf/run_95-fp16.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use deltakitsune/properly with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf deltakitsune/properly:Q8_0
# Run inference directly in the terminal:
llama-cli -hf deltakitsune/properly:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf deltakitsune/properly:Q8_0
# Run inference directly in the terminal:
llama-cli -hf deltakitsune/properly:Q8_0

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf deltakitsune/properly:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf deltakitsune/properly:Q8_0

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf deltakitsune/properly:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf deltakitsune/properly:Q8_0

Use Docker

docker model run hf.co/deltakitsune/properly:Q8_0

LM Studio
Jan

vLLM

How to use deltakitsune/properly with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/deltakitsune/properly:Q8_0

SGLang

How to use deltakitsune/properly 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 "deltakitsune/properly" \
    --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": "deltakitsune/properly",
		"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 "deltakitsune/properly" \
        --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": "deltakitsune/properly",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use deltakitsune/properly with Ollama:
```
ollama run hf.co/deltakitsune/properly:Q8_0
```

Unsloth Studio new

How to use deltakitsune/properly with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for deltakitsune/properly to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for deltakitsune/properly to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for deltakitsune/properly to start chatting

Docker Model Runner
How to use deltakitsune/properly with Docker Model Runner:
```
docker model run hf.co/deltakitsune/properly:Q8_0
```

Lemonade

How to use deltakitsune/properly with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull deltakitsune/properly:Q8_0

Run and chat with the model

lemonade run user.properly-Q8_0

List all available models

lemonade list

Properly is the proofreader that doesn't steal your voice. LoRA + Gemma 1B-IT.

Created via Kitsune : Forge.
Local: RTX 5060 Ti 16GB

This model ran through 4 epochs on curated dataset mixtures from Hugging Face, as noted in the dataset information.

Properly v1.01 — E1 During smoke testing, the adapted model performed simple edits, missed a few things, and added witty banter post-edit. And emojis.

Properly v1.02 — E2 Dropped emoji data and other social media datasets. The model improved but still loved emojis and missed a few spelling mistakes. It also treated most inputs like LinkedIn posts — complete with hashtags, occasional duplicates, and a fondness for the word "theorectical." Painful or philosophical, that misspelling proved the dataset gaps.

Properly v1.03 — E3 Added spelling data to the mix. Catches the majority of errors. No banter. Occasional rogue 🚀. Pretty solid across tested turns. "theorectical" became "theoretical."

Properly v1.04 — E4 Increased spelling and edit percentage, removed everything else, lowered steps. Adjusted learning rate from 1e-4 to 5e-5 and grad accumulation from 8 to 16. Determined that temp 0.5 with top_p 0.9 is ideal, paired with a system prompt. Eradicates most undesired behavior while preserving the author's voice. Drastically improved spelling correction. The model does struggle with informal conversational input — prompts like "OMG i loved that song im listening to" can produce a full conversation rather than a correction. This behavior has not appeared in typical email or post editing tests. Some other examples (shown below) is works > works which is still incorrect but I also stated it poorly. It did not change that kind of typo. -- imProperly? ;) A future training run should revise the dataset mix accordingly. It will still generate errors at this stage. Also found a bug in the dataviewer that leads to the zigzagging in the curve. The issue originated in E1. Finally identified that bug and corrected plus added better health checks + viewing options to Forge.

This experimentation is meant for learning and to hopefully provide useful tools — or a reference for others to learn and experiment with. The model is functional but likely not ready for unsupervised use at this point. (Though imperfect spelling and grammar has its fans in certain circles...)

Training Data

The training finished below target loss for a final product, but the model performs quite well for a 1B model on limited training and testing. The purpose was to understand model size, capability, dataset mixtures, and temperature behavior within the pipeline.

System Prompt: You are Properly a helpful assistant. You fix grammar, spelling, and clarity. Preserve the author's voice. Return only the corrected text. No explanations. No commentary. No emojis or hashtags.

Baked in for Ollama. HuggingFace users will want to add this prompt manually.

Technical Stuff.

Properly-E4-91E3-2

Summary

Training run: #95
Base model: google/gemma-3-1b-it
Artifact: Local artifact (path omitted)
Status: completed
Started: 2026-04-30T04:00:32.996087+00:00
Finished: 2026-04-30T09:22:44.290944+00:00
Final loss: 0.8404612632730544
Final accuracy: N/A - token accuracy not logged for this run type

Training Configuration

attn_implementation: eager
batch_size: 1
epochs: 1
grad_accum: 16
learning_rate: 5e-5
lora_alpha: 32
lora_dropout: 0.05
lora_rank: 16
max_grad_norm: 1
max_seq: 512
system_prompt_override: You are Properly a helpful assistant. You fix grammar, spelling, and clarity. Preserve the author's voice. Return only the corrected text. No explanations. No commentary. No emojis or hashtags.
target_examples: 50000

Dataset Configuration

Dataset Mix | 3 sources | seed 42 (mixture; 35,000 rows)

Recent Training Metrics

Accuracy is marked N/A because this run type logs causal language-model loss, not a publishable evaluation accuracy.

Step	Loss	Accuracy	LR	Epoch	Timestamp
2130 / 2188	0.8876	-	-	0.97	2026-04-30T09:14:13.929849+00:00
2140 / 2188	0.8566	-	-	0.98	2026-04-30T09:15:41.870227+00:00
2150 / 2188	0.8243	-	-	0.98	2026-04-30T09:17:06.787695+00:00
2160 / 2188	0.8341	-	-	0.99	2026-04-30T09:18:34.679929+00:00
2170 / 2188	0.8131	-	-	0.99	2026-04-30T09:20:01.712890+00:00
2180 / 2188	0.8141	-	-	1.0	2026-04-30T09:21:24.802808+00:00
2188 / 2188	0.8404612632730544	-	-	-	2026-04-30T09:22:42.250939+00:00

Deployment History

Target	Reference	Status	Created
huggingface	`deltakitsune/properly`	completed	2026-05-01T01:13:15.059197+00:00

Notes

Generated by Kitsune Training Suite. Review limitations, intended use, safety notes, and licensing before publishing.

Downloads last month: 16

GGUF

Model size

1.0B params

Architecture

gemma3

Hardware compatibility

8-bit

View +1 variant

Dataset used to train deltakitsune/properly

Collection including deltakitsune/properly

Fine Tuned via Kitsune : Forge (beta testing)

Collection

2 items • Updated 16 days ago