Instructions to use ZeusLabs/Chronos-Divergence-33B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ZeusLabs/Chronos-Divergence-33B with Transformers:

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

pipe = pipeline("text-generation", model="ZeusLabs/Chronos-Divergence-33B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ZeusLabs/Chronos-Divergence-33B")
model = AutoModelForCausalLM.from_pretrained("ZeusLabs/Chronos-Divergence-33B")
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 ZeusLabs/Chronos-Divergence-33B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ZeusLabs/Chronos-Divergence-33B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ZeusLabs/Chronos-Divergence-33B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ZeusLabs/Chronos-Divergence-33B

SGLang

How to use ZeusLabs/Chronos-Divergence-33B 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 "ZeusLabs/Chronos-Divergence-33B" \
    --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": "ZeusLabs/Chronos-Divergence-33B",
		"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 "ZeusLabs/Chronos-Divergence-33B" \
        --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": "ZeusLabs/Chronos-Divergence-33B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ZeusLabs/Chronos-Divergence-33B with Docker Model Runner:
```
docker model run hf.co/ZeusLabs/Chronos-Divergence-33B
```

Incredible model

by ricced - opened Sep 15, 2024

Discussion

ricced

Sep 15, 2024

Honestly this feels just as lively as the old character.ai did back in the day. I've tried all sorts of models since then, and this is by far the most fun to interact with. The lack of GPT-isms is also a needed breath of fresh air amidst all these smart, albeit boring models nowadays.

I'd love to see this method either be further improved upon, or tested on larger models, such as llama-65b.

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