Instructions to use elinas/chronos-13b-v2-GPTQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use elinas/chronos-13b-v2-GPTQ with Transformers:

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

pipe = pipeline("text-generation", model="elinas/chronos-13b-v2-GPTQ")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("elinas/chronos-13b-v2-GPTQ")
model = AutoModelForCausalLM.from_pretrained("elinas/chronos-13b-v2-GPTQ")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use elinas/chronos-13b-v2-GPTQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "elinas/chronos-13b-v2-GPTQ"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "elinas/chronos-13b-v2-GPTQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/elinas/chronos-13b-v2-GPTQ

SGLang

How to use elinas/chronos-13b-v2-GPTQ 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-13b-v2-GPTQ" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "elinas/chronos-13b-v2-GPTQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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-13b-v2-GPTQ" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "elinas/chronos-13b-v2-GPTQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use elinas/chronos-13b-v2-GPTQ with Docker Model Runner:
```
docker model run hf.co/elinas/chronos-13b-v2-GPTQ
```

chronos-13b-v2

This is the 4bit GPTQ of chronos-13b-v2 based on the Llama v2 Base model. It works with Exllama and AutoGPTQ.

This model is primarily focused on chat, roleplay, storywriting, with good reasoning and logic.

Chronos can generate very long outputs with coherent text, largely due to the human inputs it was trained on, and it supports context length up to 4096 tokens.

This model uses Alpaca formatting, so for optimal model performance, use and either use a frontend like SillyTavern, or continue your story with it:

### Instruction:
Your instruction or question here.
### Response:

Not using the format will make the model perform significantly worse than intended.

Quantize Config

Rename quantize_config_Xg.json where X is the groupsize to quantize_config.json for the version you pick.

Other Versions

Original FP16 Model

GGML Versions provided by @TheBloke

Support My Development of New Models

Downloads last month: 8