Downloads · 30 days
5
8% of all-time downloads
collectively-grounded-llm
cemrtkn/collectively-grounded-llm
collectively-grounded-llm is a question answering model from cemrtkn. Use it when the input is a question plus a passage. The card lists the license as mit.
This model is a full fine-tune of Llama3-8b-instruct with the dedicated dataset.
All-time downloads
66
Public
Parameters
8B
32.1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors32.1 GB · 100%
At a glance
- Task
- Question Answering
- License
- mit
- Model type
- llama
- Access
- Public
- Created
- Oct 9, 2025
- Updated
- Oct 10, 2025
- SHA
- 0cdb2dfb
Try a prompt
Base models
Model card
From the Hugging Face model README
Collectively Grounded LLM - Communism X Capitalism
This model is a full fine-tune of Llama3-8b-instruct with the dedicated dataset.
Model Details
Model Description
This model is the outcome of a summer internship carried out at Max Planck's Center for Humans and Machines group. The methodology and ideation behind the project is well documented at the repository.
Briefly, this project explores whether LLMs can better adopt collectives' perspectives by being fine-tuned on QA data generateed based on first-hand data belonging to the collectives of interest. This model constitutes a prototype for this idea producing encouraging results.
- Developed by: cemrtkn
- Association: Max Planck - Center for Humans and Machines
Model Sources
- Task
- Question Answering
- Type
- llama
- License
- mit
- Languages
- en
- Created
- Oct 9, 2025
- Updated
- Oct 10, 2025