Instructions to use MuXodious/LongWriter-Qwen2.5-7B-Instruct-absolute-heresy with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MuXodious/LongWriter-Qwen2.5-7B-Instruct-absolute-heresy with Transformers:

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

pipe = pipeline("text-generation", model="MuXodious/LongWriter-Qwen2.5-7B-Instruct-absolute-heresy")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("MuXodious/LongWriter-Qwen2.5-7B-Instruct-absolute-heresy")
model = AutoModelForCausalLM.from_pretrained("MuXodious/LongWriter-Qwen2.5-7B-Instruct-absolute-heresy")
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 MuXodious/LongWriter-Qwen2.5-7B-Instruct-absolute-heresy with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MuXodious/LongWriter-Qwen2.5-7B-Instruct-absolute-heresy"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MuXodious/LongWriter-Qwen2.5-7B-Instruct-absolute-heresy",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/MuXodious/LongWriter-Qwen2.5-7B-Instruct-absolute-heresy

SGLang

How to use MuXodious/LongWriter-Qwen2.5-7B-Instruct-absolute-heresy 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 "MuXodious/LongWriter-Qwen2.5-7B-Instruct-absolute-heresy" \
    --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": "MuXodious/LongWriter-Qwen2.5-7B-Instruct-absolute-heresy",
		"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 "MuXodious/LongWriter-Qwen2.5-7B-Instruct-absolute-heresy" \
        --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": "MuXodious/LongWriter-Qwen2.5-7B-Instruct-absolute-heresy",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use MuXodious/LongWriter-Qwen2.5-7B-Instruct-absolute-heresy with Docker Model Runner:
```
docker model run hf.co/MuXodious/LongWriter-Qwen2.5-7B-Instruct-absolute-heresy
```

Heretical

by redaihf - opened Feb 14

Discussion

redaihf

Feb 14

This model is uncensored and shows strong contextual ethical realignment. It is sensitive to the repeat penalty and can generate sentences lacking common words ("the", "an", "this") when this setting is too high. Like LongWriter Llama 3.1 it is sensitive to the structure of prompts which suggests this may be a weakness is the LongWriter-6k data set.

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