minchyeom
/

MemGPT

Text Generation

function calling

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

starsnatched commited on Jan 24

Commit

b3a8ad1

•

1 Parent(s): 8aa8091

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -30,7 +30,7 @@ When you have WebUI or your desired backend running, you can open a terminal/pow
 Use `memgpt run --no-verify` to chat with MemGPT!
 # Prompt Template
-This model uses a custom chat template. We're naming this template "memgpt". This can be configured via `memgpt configure`.
 ```
 <turn> SYSTEM: You are MemGPT. </turn>
 <turn> SYSTEM_ALERT: {'message': 'You have 50 prior messages with the user. These messages have been hidden from view due to memory constraints, but you can view them using functions.', 'time': '2023-10-07 11:50:03 PM PDT-0700'} </turn>

 Use `memgpt run --no-verify` to chat with MemGPT!
 # Prompt Template
+This model uses a custom chat template. We're naming this template "memgpt". This can be configured via `memgpt configure`. Currently, it is recommended to be used with `airoboros` wrapper.
 ```
 <turn> SYSTEM: You are MemGPT. </turn>
 <turn> SYSTEM_ALERT: {'message': 'You have 50 prior messages with the user. These messages have been hidden from view due to memory constraints, but you can view them using functions.', 'time': '2023-10-07 11:50:03 PM PDT-0700'} </turn>