Instructions to use Keynote-Technology/TinyKAI-0.7B-v0.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Keynote-Technology/TinyKAI-0.7B-v0.1 with Transformers:

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

pipe = pipeline("text-generation", model="Keynote-Technology/TinyKAI-0.7B-v0.1")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Keynote-Technology/TinyKAI-0.7B-v0.1")
model = AutoModelForCausalLM.from_pretrained("Keynote-Technology/TinyKAI-0.7B-v0.1")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Keynote-Technology/TinyKAI-0.7B-v0.1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Keynote-Technology/TinyKAI-0.7B-v0.1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Keynote-Technology/TinyKAI-0.7B-v0.1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Keynote-Technology/TinyKAI-0.7B-v0.1

SGLang

How to use Keynote-Technology/TinyKAI-0.7B-v0.1 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 "Keynote-Technology/TinyKAI-0.7B-v0.1" \
    --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": "Keynote-Technology/TinyKAI-0.7B-v0.1",
		"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 "Keynote-Technology/TinyKAI-0.7B-v0.1" \
        --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": "Keynote-Technology/TinyKAI-0.7B-v0.1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Keynote-Technology/TinyKAI-0.7B-v0.1 with Docker Model Runner:
```
docker model run hf.co/Keynote-Technology/TinyKAI-0.7B-v0.1
```

TinyKAI 0.7B

Model Details

TinyKAI-0.7B is one of the world's SMALLEST "large" language models EVER! We acheived such a feat by essentially compressing GPT2 and squeezing it to fit into one sub-GB pytorch.bin file!

Uses

Due to being one of the tiniest "large" language models on huggingface, many corners had to be cut. TinyKAI-0.7B has a max output of only 150 characters per computation (without repeating itself). Therefore, TinyKAI is only intended for research purposes.

Banned Use

TinyKAI-1B is governed by the apache 2.0 liscense, and therefore means that whatever the license deems unacceptable shall not be allowed. We specificaly ban the use of ANY AND ALL KAI MODELS for hate speech towards a paricular thing, person, our particular group due to legal and ethical issues.