|
--- |
|
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](https://github.com/unslothai/unsloth) and Huggingface's TRL library. |
|
|
|
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth) |
|
|
