webpolis
/

zenos-gpt-j-6B-instruct-4bit

Text Generation

Inference Endpoints

4-bit precision

Model card Files Files and versions Community

webpolis commited on Oct 26, 2023

Commit

49babce

•

1 Parent(s): b6cdc0d

Update README.md

Files changed (1) hide show

README.md +2 -0

README.md CHANGED Viewed

@@ -14,6 +14,8 @@
 Zenos GPT-J 6B Instruct 4-bit is a Spanish Instruction capable model based on the GPT-J architecture with 6 billion parameters. It has been fine-tuned on the Alpaca Spanish and Evol Instruct datasets, making it particularly suitable for natural language understanding and generation tasks in Spanish.
 ### Requirements
 The following **specific** up-to-date forks are required in order to load and/or manipulate the present model. At least, until the existing PRs are approved in the main repositories. They allow saving and loading 4 bits model, with LoRa adapters included.

 Zenos GPT-J 6B Instruct 4-bit is a Spanish Instruction capable model based on the GPT-J architecture with 6 billion parameters. It has been fine-tuned on the Alpaca Spanish and Evol Instruct datasets, making it particularly suitable for natural language understanding and generation tasks in Spanish.
+A experimental Twitter (**X**) bot is available at (https://twitter.com/ZenosBot)[https://twitter.com/ZenosBot] which makes comments on news published in media outlets from Argentina.
 ### Requirements
 The following **specific** up-to-date forks are required in order to load and/or manipulate the present model. At least, until the existing PRs are approved in the main repositories. They allow saving and loading 4 bits model, with LoRa adapters included.