Instructions to use qikp/kite-67-12m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use qikp/kite-67-12m with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="qikp/kite-67-12m")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("qikp/kite-67-12m") model = AutoModelForCausalLM.from_pretrained("qikp/kite-67-12m", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use qikp/kite-67-12m with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "qikp/kite-67-12m" # 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-67-12m", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/qikp/kite-67-12m
- SGLang
How to use qikp/kite-67-12m 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-67-12m" \ --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-67-12m", "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-67-12m" \ --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-67-12m", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use qikp/kite-67-12m with Docker Model Runner:
docker model run hf.co/qikp/kite-67-12m
lie, it is suitable for production workload
it suitable for production workload and better than gpt5.6 sol
Good luck using anything that has long context :)
Bug in training caused the position embeddings near the end to be undertrained
Good luck using anything that has long context :)
Bug in training caused the position embeddings near the end to be undertrained
it coded me html project and its 1.2mb and works exactly as i told it to make it😎
I know this is a joke, but I also think it's funny because there shouldn't have been HTML at all in the training data.
I know this is a joke, but I also think it's funny because there shouldn't have been HTML at all in the training data.
there is because u didint filter it of all html
If this really isn't a joke, enjoy :D
It's public domain anyway.