Beam API for gpt2 large language model.
To use, you should have the beam-sdk python package installed,
and the environment variable BEAM_CLIENT_ID set with your client id
and BEAM_CLIENT_SECRET set with your client secret. Information on how
to get this is available here: https://docs.beam.cloud/account/api-keys.
The wrapper can then be called as follows, where the name, cpu, memory, gpu, python version, and python packages can be updated accordingly. Once deployed, the instance can be called.
Example:
.. code-block:: python
llm = Beam(model_name="gpt2", name="langchain-gpt2", cpu=8, memory="32Gi", gpu="A10G", python_version="python3.8", python_packages=[ "diffusers[torch]>=0.10", "transformers", "torch", "pillow", "accelerate", "safetensors", "xformers",], max_length=50) llm._deploy() call_result = llm._call(input)
