The data used to train the model are on Huggingface under siacus/cap_pe_verified

F16 version from merged weights created with llama.cpp on a CUDA GPU and the 4bit quantized version created on a Mac M2 Ultra Metal architecture. If you want to use the 4bit quantized version on CUDA, please quantize it directly from the F16 version.

For more information about this model refer the main repository for the supplementary material of the manuscript Rethinking Scale: The Efficacy of Fine-Tuned Open-Source LLMs in Large-Scale Reproducible Social Science Research.

Downloads last month: 15

GGUF

Model size

7B params

Architecture

llama

Hardware compatibility

4-bit

16-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for siacus/llama-2-7b-cap_verified

Base model

meta-llama/Llama-2-7b-chat-hf

Quantized

(103)

this model

Dataset used to train siacus/llama-2-7b-cap_verified

Paper for siacus/llama-2-7b-cap_verified

Rethinking Scale: The Efficacy of Fine-Tuned Open-Source LLMs in Large-Scale Reproducible Social Science Research

Paper • 2411.00890 • Published Oct 31, 2024