Instructions to use pfnet/plamo-2-1b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use pfnet/plamo-2-1b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="pfnet/plamo-2-1b", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("pfnet/plamo-2-1b", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use pfnet/plamo-2-1b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "pfnet/plamo-2-1b" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "pfnet/plamo-2-1b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/pfnet/plamo-2-1b
- SGLang
How to use pfnet/plamo-2-1b 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 "pfnet/plamo-2-1b" \ --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": "pfnet/plamo-2-1b", "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 "pfnet/plamo-2-1b" \ --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": "pfnet/plamo-2-1b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use pfnet/plamo-2-1b with Docker Model Runner:
docker model run hf.co/pfnet/plamo-2-1b
Add link to Github repository
#4
by nielsr HF Staff - opened
This PR adds a link to the Github repository for the Samba model, as mentioned in the paper. This makes it easier for users to access the training code.
Thank you for submitting the pull request.
We apologize for any confusion caused by the inaccurate README. The PLaMo 2 architecture is not exactly the same as Samba.
Here are the reasons for the differences:
- We needed normalization similar to Jamba to enhance training stability.
- We adopted the Mamba2 kernel to improve computation speed.
We have updated the README to include this information.