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

Libraries

How to use schonsense/Diagesis with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("schonsense/Diagesis")
model = AutoModelForCausalLM.from_pretrained("schonsense/Diagesis")
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

vLLM

How to use schonsense/Diagesis with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/schonsense/Diagesis

SGLang

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

Docker Model Runner
How to use schonsense/Diagesis with Docker Model Runner:
```
docker model run hf.co/schonsense/Diagesis
```

UGI Leaderboards - the highest score for "readability_grade_level"

by GeoMaciolek - opened Feb 4

Discussion

GeoMaciolek

Feb 4

I thought you might want to know - this model tested with the highest "readability grade level" (nominally meaning "the grade level required for someone to understand" / wildest vocabulary) in the Uncensored General Intelligence (UGI) Leaderboards

With a score of 12.7, it's not even close. The next ones:

10.9: Qwen3-Coder-REAP-25B-A3B 10.9
10.8: gemma-2-Ifable-9B
10.6: amoral-gemma3-4B-v2
9.8: NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 (chatml w/ <think> prefill)
9.6: amoral-gemma3-1B-v2

The "writing" score actually targets a grade level of 5.5, based on the author's surveying of user preferences, but, I think there's something special about where yours is at! (Yours also ranks pretty high in terms of "leaning dark" and "leaning nsfw", though not anything absurdly high)

schonsense

Owner Feb 4

Thank you. I'm glad someone is getting something out of these experimental models.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment