Instructions to use MaLA-LM/mala-500-10b-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use MaLA-LM/mala-500-10b-v1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="MaLA-LM/mala-500-10b-v1")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("MaLA-LM/mala-500-10b-v1", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use MaLA-LM/mala-500-10b-v1 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "MaLA-LM/mala-500-10b-v1" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "MaLA-LM/mala-500-10b-v1", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/MaLA-LM/mala-500-10b-v1
- SGLang
How to use MaLA-LM/mala-500-10b-v1 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 "MaLA-LM/mala-500-10b-v1" \ --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": "MaLA-LM/mala-500-10b-v1", "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 "MaLA-LM/mala-500-10b-v1" \ --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": "MaLA-LM/mala-500-10b-v1", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use MaLA-LM/mala-500-10b-v1 with Docker Model Runner:
docker model run hf.co/MaLA-LM/mala-500-10b-v1
Cannot load tokenizer with `transformers<4.36.1` (TypeError: unhashable type: 'dict')
#4
by gegallego - opened
Hello,
Thanks for your important contribution to the field :D
I want to inform that the tokenizer is affected by an issue described here, which is solved in the Patch release v4.36.1.
Therefore, the model can only be used with transformers>=4.36.1, maybe you should specify it in the README.
Best regards,
Gerard
how do we by-pass the mismatch in vocabulary sizes when merging?
nevermind. fixed it
jisx changed discussion status to closed