Instructions to use teknium/airoboros-mistral2.2-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use teknium/airoboros-mistral2.2-7b with Transformers:

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

pipe = pipeline("text-generation", model="teknium/airoboros-mistral2.2-7b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("teknium/airoboros-mistral2.2-7b")
model = AutoModelForCausalLM.from_pretrained("teknium/airoboros-mistral2.2-7b")

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use teknium/airoboros-mistral2.2-7b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "teknium/airoboros-mistral2.2-7b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "teknium/airoboros-mistral2.2-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/teknium/airoboros-mistral2.2-7b

SGLang

How to use teknium/airoboros-mistral2.2-7b 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 "teknium/airoboros-mistral2.2-7b" \
    --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": "teknium/airoboros-mistral2.2-7b",
		"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 "teknium/airoboros-mistral2.2-7b" \
        --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": "teknium/airoboros-mistral2.2-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use teknium/airoboros-mistral2.2-7b with Docker Model Runner:
```
docker model run hf.co/teknium/airoboros-mistral2.2-7b
```

Airboros prompt format?

by cogbuji - opened Oct 4, 2023

Discussion

cogbuji

Oct 4, 2023

The model card looks like it uses the Vicuna prompt format. Does it not support the Airboros prompt format (in particular, the context-obedient question-answering format)?

teknium

Owner Oct 5, 2023

The model card looks like it uses the Vicuna prompt format. Does it not support the Airboros prompt format (in particular, the context-obedient question-answering format)?

If you can fit it in the vicuna format it can

sephwalker3

Feb 11, 2024

What exactly does this mean? "If you can fit it in the vicuna format"? I've repeatedly come back to this post trying to comprehend this and no matter how many times I see this, I still don't understand. I'm certainly being an idiot, and would very much appreciate it if you could explain this to me in a bit more detail. Thanks in advance for your time. <3

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