Instructions to use core-outline/chronos with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use core-outline/chronos with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("core-outline/chronos")
model = AutoModelForCausalLM.from_pretrained("core-outline/chronos")
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 core-outline/chronos with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/core-outline/chronos

SGLang

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

Docker Model Runner
How to use core-outline/chronos with Docker Model Runner:
```
docker model run hf.co/core-outline/chronos
```

Model Card for Model ID

Model Details

Model Description

This model is a quantized and fine-tuned version of gemma-2b-it instruction model

Developed by: Core&Outline
Finetuned from model google/gemma-2b-it: [More Information Needed]

Model Sources [optional]

Repository: [More Information Needed]
Paper [optional]: [More Information Needed]
Demo [optional]: [More Information Needed]

Uses

To use this model via inference API or otherwise please ensure to follow the Google formatting. Ensure that your prompt is preceeded with user {{prompt}} model

Recommendations

Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.

How to Get Started with the Model

Use the code below to get started with the model.

[More Information Needed]

Training Details

Training Data

Fine tuning was done using an internal dataset here: https://huggingface.co/datasets/core-outline/llama-2-7b-chat-hf

[More Information Needed]

Training Procedure

Training was done manually on an NVIDIA-T4 instance. Find the code to the training procedure here: https://github.com/Core-Outline/core-transformer-network/blob/master/GemmaFineTuning.ipynb

Downloads last month: 1

Safetensors

Model size

3B params

Tensor type

F16

core-outline
/

chronos