Blog
Replicate
STABLE

Falcon 40B Instruct

A 40 billion parameter language model trained to follow human instructions.

Inputs
Prompt
Prompt to send to the model.
Debug
provide debugging output in logs
Length Penalty
Increasing the length_penalty parameter above 1.0 will cause the model to favor longer sequences, while decreasing it below 1.0 will cause the model to favor shorter sequences.
Max Length
Maximum number of tokens to generate. A word is generally 2-3 tokens
No Repeat Ngram Size
If set to int > 0, all ngrams of size no_repeat_ngram_size can only occur once.
Output Index
If output is a list, which element to use
Repetition Penalty
Penalty for repeated words in generated text; 1 is no penalty, values greater than 1 discourage repetition, less than 1 encourage it.
Seed
Set seed for reproducible outputs. Set to -1 for random seed.
Stop Sequences
Comma delimited string specifying stop sequences. Multi-token stop sequences are supported, but they cannot contain commas.
Temperature
Adjusts randomness of outputs, greater than 1 is random and 0 is deterministic, 0.75 is a good starting value.
Top P
When decoding text, samples from the top p percentage of most likely tokens; lower to ignore less likely tokens
Outputs
Value
The output string