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

Libraries

How to use Austism/chronos-hermes-13b with Transformers:

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

pipe = pipeline("text-generation", model="Austism/chronos-hermes-13b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Austism/chronos-hermes-13b")
model = AutoModelForCausalLM.from_pretrained("Austism/chronos-hermes-13b")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Austism/chronos-hermes-13b with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Austism/chronos-hermes-13b

SGLang

How to use Austism/chronos-hermes-13b 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 "Austism/chronos-hermes-13b" \
    --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": "Austism/chronos-hermes-13b",
		"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 "Austism/chronos-hermes-13b" \
        --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": "Austism/chronos-hermes-13b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Austism/chronos-hermes-13b with Docker Model Runner:
```
docker model run hf.co/Austism/chronos-hermes-13b
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

(chronos-13b + Nous-Hermes-13b) 75/25 merge

This has the aspects of chronos's nature to produce long, descriptive outputs. But with additional coherency and an ability to better obey instructions. Resulting in this model having a great ability to produce evocative storywriting and follow a narrative.

This mix contains alot of chronos's writing style and 'flavour' with far less tendency of going AWOL and spouting nonsensical babble.

This result was much more successful than my first chronos merge.

Downloads last month: 30

Model tree for Austism/chronos-hermes-13b

Quantizations

5 models

Austism
/

chronos-hermes-13b

Model tree for Austism/chronos-hermes-13b

Spaces using Austism/chronos-hermes-13b 20