← Back to all generators

replicate/llama-7b

Transformers implementation of the LLaMA language model

Capabilities

Top-P

Cost

Community model (estimated from hardware time)

Input Parameters

prompt required string

Text to prefix with 'hello '

max_gen_len integer

Max generation length

Default: 256
temperature number

Temperature

Default: 0.8
top_p number

Top p value

Default: 0.95
Version: 03d3a482ec4f Updated: 2/26/2026 99.4K runs