Instructions to use 7erminalVelociraptor/Airochronos-33b-Guanaco with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use 7erminalVelociraptor/Airochronos-33b-Guanaco with Transformers:

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

pipe = pipeline("text-generation", model="7erminalVelociraptor/Airochronos-33b-Guanaco")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("7erminalVelociraptor/Airochronos-33b-Guanaco")
model = AutoModelForCausalLM.from_pretrained("7erminalVelociraptor/Airochronos-33b-Guanaco", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use 7erminalVelociraptor/Airochronos-33b-Guanaco with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "7erminalVelociraptor/Airochronos-33b-Guanaco"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "7erminalVelociraptor/Airochronos-33b-Guanaco",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/7erminalVelociraptor/Airochronos-33b-Guanaco

SGLang

How to use 7erminalVelociraptor/Airochronos-33b-Guanaco 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 "7erminalVelociraptor/Airochronos-33b-Guanaco" \
    --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": "7erminalVelociraptor/Airochronos-33b-Guanaco",
		"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 "7erminalVelociraptor/Airochronos-33b-Guanaco" \
        --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": "7erminalVelociraptor/Airochronos-33b-Guanaco",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use 7erminalVelociraptor/Airochronos-33b-Guanaco with Docker Model Runner:
```
docker model run hf.co/7erminalVelociraptor/Airochronos-33b-Guanaco
```

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

This is Henk717's merge of Chronos and Airoboros 1.4 with Timdetmer's Guanaco applied as a lora.

Mainly intended for character roleplay and creative writing. Initial testing suggests it does a reasonable job at this, but it is too early to say how it compares to Airochronos. Other tasks such as coding or logic has not been reviewed.

The model has been tested with Alpaca's prompt style ( ### Instruction: and ### Response: ), as this is what Chronos and Guanaco use.

Keep in mind that all parts of this model are not censored, and thus can output NSFW or other unfiltered content. Use at your own discretion.

Downloads last month: 3