Instructions to use MWirelabs/Kren-M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use MWirelabs/Kren-M with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="MWirelabs/Kren-M")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("MWirelabs/Kren-M") model = AutoModelForCausalLM.from_pretrained("MWirelabs/Kren-M") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use MWirelabs/Kren-M with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "MWirelabs/Kren-M" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "MWirelabs/Kren-M", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/MWirelabs/Kren-M
- SGLang
How to use MWirelabs/Kren-M 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 "MWirelabs/Kren-M" \ --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": "MWirelabs/Kren-M", "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 "MWirelabs/Kren-M" \ --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": "MWirelabs/Kren-M", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use MWirelabs/Kren-M with Docker Model Runner:
docker model run hf.co/MWirelabs/Kren-M
Request for Access to Kren-M Model
Hi MWire Labs Team,
I requested access to the Kren-M model on Hugging Face on June 12, and my request is still in the "Pending" state.
I'm part of the engineering team working on the VallamAI platform - https://www.madhifoundation.org/programmes/in-the-works/vallam-ai . We're currently building and preparing to launch our application for Meghalaya, where support for local languages is a key requirement. Kren-M appears to be a great fit for our use case, and we'd like to evaluate and integrate it into our pipeline.
Could you please review my access request when you have a chance?
Hugging Face username: Nishantkumar12
Thank you for your time and for making this model available. We appreciate your support and look forward to exploring Kren-M for our Meghalaya deployment.
Hi MWire Labs Team,
I wanted to follow up on my request for access to the Kren-M model on Hugging Face. I requested access on June 12, and it still appears to be in the Pending state.
Our team is actively working on the VallamAI platform and is preparing for our Meghalaya deployment. We’re currently at the stage where we need to evaluate and integrate Kren-M into our pipeline, so access has become time-sensitive.
If possible, we’d greatly appreciate it if you could review and approve my request when you have a chance.
Hugging Face username: Nishantkumar12
Thank you for your time and support. We look forward to evaluating Kren-M for our deployment.