Instructions to use xenon111/neur-0.0-full with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use xenon111/neur-0.0-full with Transformers:

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

pipe = pipeline("text-generation", model="xenon111/neur-0.0-full", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("xenon111/neur-0.0-full", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("xenon111/neur-0.0-full", trust_remote_code=True)
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 xenon111/neur-0.0-full with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "xenon111/neur-0.0-full"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "xenon111/neur-0.0-full",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/xenon111/neur-0.0-full

SGLang

How to use xenon111/neur-0.0-full 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 "xenon111/neur-0.0-full" \
    --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": "xenon111/neur-0.0-full",
		"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 "xenon111/neur-0.0-full" \
        --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": "xenon111/neur-0.0-full",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use xenon111/neur-0.0-full with Docker Model Runner:
```
docker model run hf.co/xenon111/neur-0.0-full
```

🧠 Neur-0.0-Full

Fine-tuned variant of openai/gpt-oss-20b using supervised fine-tuning (SFT) with QLoRA adapters, later merged into a full standalone model.

📋 Overview

Neur n0.0 is a 20B-parameter transformer language model derived from GPT-OSS-20B, fine-tuned to improve reasoning, coding, and multi-step tool-use behaviors.

n0.0 is intended to be used in conjunction with Agentic tools for the purpose of helping the user complete everyday tasks on the computer.

It can also directly write or edit code on any IDE or platform at the user's request.

This release merges LoRA adapters into the base model so it can be loaded directly with from_pretrained()—no external adapter weights required.

🔧 Model Details

Attribute	Value
Base Model	`openai/gpt-oss-20b`
Architecture	Decoder-only Transformer (GPT-style)
Parameters	~20.9B
Precision	bfloat16 (BF16)
Fine-tuning Method	QLoRA (4-bit quantization, r=16, α=32)
Dataset	CodeAlpaca-20k + curated reasoning data
Training Steps	1500
Optimizer	AdamW with cosine LR schedule
Output Directory	`out-sft-qlora/merged-standalone`
Frameworks	🤗 Transformers, PEFT, BitsAndBytes, Accelerate

🚀 Usage

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

model_id = "xenon111/neur-0.0-full"

tok = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    device_map="auto",
    dtype=torch.bfloat16 if torch.cuda.is_available() and torch.cuda.is_bf16_supported()
           else (torch.float16 if torch.cuda.is_available() else torch.float32),
    trust_remote_code=True,
)

prompt = "Write a Python function that sorts a list of numbers using merge sort."
inputs = tok(prompt, return_tensors="pt").to(model.device)
output = model.generate(**inputs, max_new_tokens=200, temperature=0.7)
print(tok.decode(output[0], skip_special_tokens=True))

Downloads last month: 1

Safetensors

Model size

21B params

Tensor type

BF16

Model tree for xenon111/neur-0.0-full

Base model

openai/gpt-oss-20b

Finetuned

(511)

this model

xenon111
/

neur-0.0-full

🧠 Neur-0.0-Full

📋 Overview

🔧 Model Details

🚀 Usage

Model tree for xenon111/neur-0.0-full

Dataset used to train xenon111/neur-0.0-full