Instructions to use z-lab/Kimi-K2.6-DFlash with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use z-lab/Kimi-K2.6-DFlash with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="z-lab/Kimi-K2.6-DFlash")# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("z-lab/Kimi-K2.6-DFlash") model = AutoModel.from_pretrained("z-lab/Kimi-K2.6-DFlash", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use z-lab/Kimi-K2.6-DFlash with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "z-lab/Kimi-K2.6-DFlash" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "z-lab/Kimi-K2.6-DFlash", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/z-lab/Kimi-K2.6-DFlash
- SGLang
How to use z-lab/Kimi-K2.6-DFlash 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 "z-lab/Kimi-K2.6-DFlash" \ --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": "z-lab/Kimi-K2.6-DFlash", "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 "z-lab/Kimi-K2.6-DFlash" \ --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": "z-lab/Kimi-K2.6-DFlash", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use z-lab/Kimi-K2.6-DFlash with Docker Model Runner:
docker model run hf.co/z-lab/Kimi-K2.6-DFlash
Please kindly approve my request to access this model
@jianchen0311 thx!
Also :-|
🙏
me too,thanks
🙏
me too,thanks
could you please help me with access also?
Could you please approve access for me as well thank you 🙏
me too,thanks
same here, thnx
me too,thanks
Please approve the request
Thank you for this amazing work! Could you please approve access 🙏
could i also get access? thanks a lot!
me too,thanks!@jianchen0311
me too,thanks
Did anyone actually get the model?
Nope
me too,thanks
me too, thanks
Me too, thanks!
Me too, thanks!
me too,thanks
hello, can you give us access? THX
same here, was going to write a blog post about this