LLM Explorer

Chat Sandbox

The Chat UI in LLM explorer offers an experience similar to the OpenAI chat sandbox for writing zero and multi-shot prompts for use in agents.

System Message: Defines the system message to send to the LLM model(s). This is formatted and prepended to the input/output examples.
Top K: Adjust the top K parameter (default is 50).
Top P: Adjust the top P parameter (default is 0.9).
Min P: Adjust the minimum P parameter (default is 0.05).
Temperature: Adjust the temperature setting (default is 1).
Mirostat: Turn the mirostat setting on or off (default is off).
Seed: Set the seed for generation. Default is -1 (random).

#1 Add/Remove input examples The plus and minus button in the lower left-hand corner allow for the addition and removal of input/output example pairs to feed into the model(s).
#2 Max completion tokens Max number of completion tokens
#3 Number of Generations Number of generations per model
#4 Model(s) Selector Multi-select list of models to test
#5 Copy to Clipboard Copies the output to the clipboard.
#6 Model name The name of the model producing the completion tokens.
#7 Token stats Stats on how long each token took and other totals.

#1 Input Example Example input data to feed the model.
#2 Output Example Expected output from the model.
#3 Copy to Input Copies the example input to the input box, useful for testing validation pairs on new models.
#4 Exclude Example Do not pass the input and output example to the model. This is useful for storing validation pairs.

The Completion UI offer a way to interact with LLM models in the rawest form. After each generation you can change whatever you want and rerun 🚀