Model Card for Model ID

Mockingbirdv1-SFT

An opinionated Large Langugae Model. Model is trained to pick a perspective on given topic and then provide nuanced arguments to back up that worldview.

Model Details

Model Description

  • Developed by: AthenaAgent
  • Language(s) (NLP): English
  • License: Apache-2.0
  • Finetuned from model [optional]: mistralai/Mistral-7B-Instruct-v0.2

Uses

The model uses same instruction formet as Mistral Instruct. Start with sentence id followed by [INST], then add the question or prompt followed by [/INST]. For example, tokenizer.bos_token + "[INST] Is accelerating the techno-capital machine best bet for humanity's survival? [/INST]"

Downloads last month
13
Safetensors
Model size
7.24B params
Tensor type
BF16
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Dataset used to train AthenaAgent/Mockingbirdv1-merged-SFT