tinyllama / README.md
jan-hq's picture
Update README.md
9f05117 verified
|
raw
history blame
450 Bytes
metadata
license: apache-2.0

Download a Model

cortex models pull tinyllama

Start the Engine

cortex engines

Start model

cortex models start tinyllama

Chat

cortex chat

Model Structure

1.1b-chat-v1.0-gguf-Q2_K
1.1b-chat-v1.0-gguf-Q4_K_M
1.1b-chat-v1.0-gguf-Q6_K
1.1b-chat-v1.0-gguf-Q8_0
1.1b-chat-v1.0-tensorrtllm-ada_windows
1.1b-chat-v1.0-tensorrtllm-turing_windows
1.1b-chat-v1.0-tensorrtllm-ampere_windows