0.5

• New -o max_gen_len 100 option for setting the maximum length of the generated text. #10

0.4

• The llm mlc download-model command now takes zero or more optional -a/--alias options to configure aliases for the model once it has been installed. #4:

  llm mlc download-model Llama-2-7b-chat --alias llama2

• Installation instructions are clearer, and show how to install required dependencies first. #6
• The plugin no longer crashes llm if it cannot find the dist/prebuilt folder. #9
• New options for temperature, top_p and repetition_penalty: #7

  llm -m Llama-2-7b-chat \
    -o temperature 0.5 \
    -o top_p 0.9 \
    -o repetition_penalty 0.9 \
    'five names for a cute pet ferret'

0.3

• Conversation mode now works, so you can continue a conversation with an MLC model with llm -c "follow-up prompt". #3

0.2

• Token streaming now works. #2

0.1a0

• Initial release. Tools for installing and running MLC models using LLM. #1