Instructions to use BK-Lee/Meteor-Mamba with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use BK-Lee/Meteor-Mamba with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="BK-Lee/Meteor-Mamba")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("BK-Lee/Meteor-Mamba") model = AutoModelForCausalLM.from_pretrained("BK-Lee/Meteor-Mamba") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use BK-Lee/Meteor-Mamba with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "BK-Lee/Meteor-Mamba" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "BK-Lee/Meteor-Mamba", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/BK-Lee/Meteor-Mamba
- SGLang
How to use BK-Lee/Meteor-Mamba 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 "BK-Lee/Meteor-Mamba" \ --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": "BK-Lee/Meteor-Mamba", "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 "BK-Lee/Meteor-Mamba" \ --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": "BK-Lee/Meteor-Mamba", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use BK-Lee/Meteor-Mamba with Docker Model Runner:
docker model run hf.co/BK-Lee/Meteor-Mamba
thank you!
#2
by MicFizzy - opened
Hello BK-Lee!
Thank you so much for sharing this model. Do we have a gguf version of the model so I can try it in Ollama or LMstudio?
also, is the model ok for finetuning?
Thank you so much in advance!!
Liz
you can load mamba from safetensor and then download the format of "gguf"
Is it not working? actually I did not have an experience of saving gguf version
I will try and get back to you! Thank you so much~~
Liz