Here's an HTML page summarizing the LLM plugins with usage examples:
Access models hosted by Anyscale Endpoints.
llm -m mistralai/Mixtral-8x22B-Instruct-v0.1 \ 'Five strident names for a pet walrus' \ --system 'You love coming up with creative names for pets'
Access Claude 3 models by Anthropic.
llm -m claude-3.5-sonnet 'Fun facts about pelicans' llm -m claude-3-opus 'Fun facts about squirrels' llm -m claude-3-sonnet 'Fun facts about walruses' llm -m claude-3-haiku 'Fun facts about armadillos'
Embed images and text using CLIP.
llm embed -m clip -c 'Hello world' llm embed -m clip --binary -i IMG_4801.jpeg
Cluster embeddings stored in a collection.
llm cluster llm-issues 10 \ -d issues.db \ --summary \ --model gpt-4
Generate and execute shell commands.
llm cmd undo last git commit
Access Cohere Command R models.
llm -m command-r 'What is the LLM CLI tool?' -o websearch 1
Run models distributed as GGUF files.
llm -m gguf/Meta-Llama-3.1-8B-Instruct-Q4_K_M 'Five great names for a pet lemur'
Access GPT4All models.
llm -m mistral-7b-instruct-v0 'How much is 2+2?'
Access Mistral AI models.
llm -m mistral-tiny 'A sassy name for a pet sasquatch'
Access OpenAI language and embedding models.
llm -m gpt-3.5-turbo "Write a haiku about data"
Access models hosted on Replicate.
llm -m llama2 "Ten great names for a pet pelican"
Use sentence-transformers embedding models.
llm embed -m mpnet -c "Hello world"