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
15
Safetensors
Model size
7.24B params
Tensor type
BF16
·
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.

Dataset used to train AthenaAgent/Mockingbirdv1-merged-SFT