OA-Pythia-12B-SFT-4

This is the 4th iteration English supervised-fine-tuning (SFT) model of the Open-Assistant project. It is based on a Pythia 12B that was fine-tuned on human demonstrations of assistant conversations collected through the https://open-assistant.io/ human feedback web app before March 25, 2023.

Model Details

• Developed by: Open-Assistant Contributors
• Model type: Transformer-based Language Model
• Language: English
• Finetuned from: EleutherAI / pythia-12b-deduped
• Code: Open-Assistant/model/model_training
• Demo: Continuations for 250 random prompts
• License: Apache 2.0
• Contact: Open-Assistant Discord

Prompting

Two special tokens are used to mark the beginning of user and assistant turns: <|prompter|> and <|assistant|>. Each turn ends with a <|endoftext|> token.

Input prompt example:

<|prompter|>What is a meme, and what's the history behind this word?<|endoftext|><|assistant|>

The input ends with the <|assistant|> token to signal that the model should start generating the assistant reply.

免责声明

OA-Pythia-12B-SFT-4模型来源于第三方，百度智能云千帆大模型平台不保证其合规性，请您在使用前慎重考虑，确保合法合规使用并遵守第三方的要求。

具体请查看模型的开源协议Apache 2.0及模型开源页面展示信息等。

如您发现模型/数据集/文件等有任何问题，请及时联系我们处理。