Instructions to use elinas/Chronos-Gold-12B-1.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use elinas/Chronos-Gold-12B-1.0 with Transformers:

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

pipe = pipeline("text-generation", model="elinas/Chronos-Gold-12B-1.0")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("elinas/Chronos-Gold-12B-1.0")
model = AutoModelForCausalLM.from_pretrained("elinas/Chronos-Gold-12B-1.0")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use elinas/Chronos-Gold-12B-1.0 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "elinas/Chronos-Gold-12B-1.0"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "elinas/Chronos-Gold-12B-1.0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/elinas/Chronos-Gold-12B-1.0

SGLang

How to use elinas/Chronos-Gold-12B-1.0 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 "elinas/Chronos-Gold-12B-1.0" \
    --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": "elinas/Chronos-Gold-12B-1.0",
		"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 "elinas/Chronos-Gold-12B-1.0" \
        --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": "elinas/Chronos-Gold-12B-1.0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use elinas/Chronos-Gold-12B-1.0 with Docker Model Runner:
```
docker model run hf.co/elinas/Chronos-Gold-12B-1.0
```

Impressed

by Ardvark123 - opened Aug 28, 2024

Discussion

Ardvark123

Aug 28, 2024

I have to say, I have tried tons of Nemo models. None really touched the original, it always felt either dumber, or gptish. (or not sexy when the time was right) this one follows prompts fantastically, it's clever, seems to have its own personality and I have yet to find a shiver down my spine or other classics. Best nemo finetune thus far and by a large margin.

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