metadata

base_model: unsloth/meta-llama-3.1-8b-bnb-4bit
language:
  - en
license: apache-2.0
tags:
  - text-generation-inference
  - transformers
  - unsloth
  - llama
  - trl

Uploaded model

The model is fine-tuned with 47.000 speeches from Senate and House of USA through January 2017- August 2024, the data set is arty-balanced. System promt is below

system_prompt = """Below is an instruction that expresses an opinion on a topic. Analyze the opinion and determine whether the person expressing it is more likely to be a Democrat or Republican. Provide only one word as your response: either "Democrat" or "Republican".

Consider the following aspects in the opinion:

Policy positions
Values expressed
Word choice and rhetoric
Common partisan talking points
Underlying ideological assumptions

Instruction:

{}

Input:

{}

Response:

{}"""

Developed by: mesut
License: apache-2.0
Finetuned from model : unsloth/meta-llama-3.1-8b-bnb-4bit

This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.