Instructions to use qikp/kite-4.2-14m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use qikp/kite-4.2-14m with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="qikp/kite-4.2-14m")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("qikp/kite-4.2-14m") model = AutoModelForCausalLM.from_pretrained("qikp/kite-4.2-14m", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use qikp/kite-4.2-14m with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "qikp/kite-4.2-14m" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "qikp/kite-4.2-14m", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/qikp/kite-4.2-14m
- SGLang
How to use qikp/kite-4.2-14m 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 "qikp/kite-4.2-14m" \ --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": "qikp/kite-4.2-14m", "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 "qikp/kite-4.2-14m" \ --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": "qikp/kite-4.2-14m", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use qikp/kite-4.2-14m with Docker Model Runner:
docker model run hf.co/qikp/kite-4.2-14m
|
Download README.md from qikp/kite-4.2-14m: direct link, hf CLI and curl.
- Browser
- Download file 797 Bytes
-
https://huggingface.co/qikp/kite-4.2-14m/resolve/main/README.md
- Command line
-
hf download hf://qikp/kite-4.2-14m/README.md
-
curl -L -o README.md https://huggingface.co/qikp/kite-4.2-14m/resolve/main/README.md
797 Bytes
metadata
license: cc0-1.0
datasets:
- qikp/small-data-2
language:
- en
pipeline_tag: text-generation
library_name: transformers
Kite
🎉 You are looking at Kite 4.2, which is using a more optimized dataset!
Kite is a small, trained, 14 million parameter language model.
Training
It was trained on a tokenized version of qikp/small-data-2, which is a mixture of various datasets, using 1 epoch, 32 batch size, 1.5e-4 learning rate, and the pika 4 tokenizer.
Also, evaluation on a tokenized and truncated byunggill/gpt-2-output was done during training.
Limitations
Due to its size, the model is not suitable for production workloads.