Instructions to use p-e-w/Oc-e-Non-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use p-e-w/Oc-e-Non-v1 with Transformers:

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

pipe = pipeline("text-generation", model="p-e-w/Oc-e-Non-v1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("p-e-w/Oc-e-Non-v1")
model = AutoModelForCausalLM.from_pretrained("p-e-w/Oc-e-Non-v1", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use p-e-w/Oc-e-Non-v1 with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/p-e-w/Oc-e-Non-v1

SGLang

How to use p-e-w/Oc-e-Non-v1 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 "p-e-w/Oc-e-Non-v1" \
    --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": "p-e-w/Oc-e-Non-v1",
		"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 "p-e-w/Oc-e-Non-v1" \
        --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": "p-e-w/Oc-e-Non-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use p-e-w/Oc-e-Non-v1 with Docker Model Runner:
```
docker model run hf.co/p-e-w/Oc-e-Non-v1
```

p-e-w commited on about 8 hours ago

Commit

dbf4e26

verified ·

1 Parent(s): 67de02f

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -12,7 +12,7 @@ tags:
 Oc-e-Non-v1 is a *tersified* version of [Qwen/Qwen3-4B-Instruct-2507](https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507), made using [Heretic](https://heretic-project.org) v2.1.0.dev0. **It reduces Qwen's mean response length by 50%.**
-You can produce similar results using Heretic's [`config.terse.toml` configuration file](https://github.com/p-e-w/heretic/blob/ce61e18206990bc1f4c51a6cbecd1bfee4b631bb/config.terse.toml).
 &nbsp;

 Oc-e-Non-v1 is a *tersified* version of [Qwen/Qwen3-4B-Instruct-2507](https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507), made using [Heretic](https://heretic-project.org) v2.1.0.dev0. **It reduces Qwen's mean response length by 50%.**
+You can produce similar models yourself using Heretic's [`config.terse.toml` configuration file](https://github.com/p-e-w/heretic/blob/ce61e18206990bc1f4c51a6cbecd1bfee4b631bb/config.terse.toml).
 &nbsp;