Instructions to use ScottzillaSystems/ChatGPT-5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ScottzillaSystems/ChatGPT-5 with Transformers:

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

pipe = pipeline("text-generation", model="ScottzillaSystems/ChatGPT-5")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ScottzillaSystems/ChatGPT-5")
model = AutoModelForCausalLM.from_pretrained("ScottzillaSystems/ChatGPT-5")
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 ScottzillaSystems/ChatGPT-5 with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/ScottzillaSystems/ChatGPT-5

SGLang

How to use ScottzillaSystems/ChatGPT-5 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 "ScottzillaSystems/ChatGPT-5" \
    --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": "ScottzillaSystems/ChatGPT-5",
		"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 "ScottzillaSystems/ChatGPT-5" \
        --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": "ScottzillaSystems/ChatGPT-5",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ScottzillaSystems/ChatGPT-5 with Docker Model Runner:
```
docker model run hf.co/ScottzillaSystems/ChatGPT-5
```

ChatGPT-5 / README.md

ScottzillaSystems

fix: add pipeline_tag, library_name, and conversational tag for inference compatibility

9dcd6cc verified 11 days ago

preview code

raw

history blame contribute delete

1.14 kB

metadata

license: apache-2.0
library_name: transformers
pipeline_tag: text-generation
base_model:
  - Qwen/Qwen2.5-0.5B-Instruct
tags:
  - conversational
  - safetensors
  - qwen2

ChatGPT-5

Ultra-fast AI chat model based on Qwen2.5-0.5B-Instruct architecture (494M parameters).

Features

⚡ Ultra-fast — Lightweight 494M parameter model for instant responses
💬 Conversational — Optimized for multi-turn chat
🔧 Instruction Following — Follows instructions accurately

Chat UI

Try it now: ChatGPT-5 Chat

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("ScottzillaSystems/ChatGPT-5")
tokenizer = AutoTokenizer.from_pretrained("ScottzillaSystems/ChatGPT-5")

messages = [{"role": "user", "content": "Hello!"}]
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(text, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=512)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))