Quantization made by Richard Erkhov.

tabula-8b - GGUF

Model creator: https://huggingface.co/mlfoundations/
Original model: https://huggingface.co/mlfoundations/tabula-8b/

Name	Quant method	Size
tabula-8b.Q2_K.gguf	Q2_K	2.96GB
tabula-8b.IQ3_XS.gguf	IQ3_XS	3.28GB
tabula-8b.IQ3_S.gguf	IQ3_S	3.43GB
tabula-8b.Q3_K_S.gguf	Q3_K_S	3.41GB
tabula-8b.IQ3_M.gguf	IQ3_M	3.52GB
tabula-8b.Q3_K.gguf	Q3_K	3.74GB
tabula-8b.Q3_K_M.gguf	Q3_K_M	3.74GB
tabula-8b.Q3_K_L.gguf	Q3_K_L	4.03GB
tabula-8b.IQ4_XS.gguf	IQ4_XS	4.18GB
tabula-8b.Q4_0.gguf	Q4_0	4.34GB
tabula-8b.IQ4_NL.gguf	IQ4_NL	4.38GB
tabula-8b.Q4_K_S.gguf	Q4_K_S	4.37GB
tabula-8b.Q4_K.gguf	Q4_K	4.58GB
tabula-8b.Q4_K_M.gguf	Q4_K_M	4.58GB
tabula-8b.Q4_1.gguf	Q4_1	4.78GB
tabula-8b.Q5_0.gguf	Q5_0	5.21GB
tabula-8b.Q5_K_S.gguf	Q5_K_S	5.21GB
tabula-8b.Q5_K.gguf	Q5_K	5.34GB
tabula-8b.Q5_K_M.gguf	Q5_K_M	5.34GB
tabula-8b.Q5_1.gguf	Q5_1	5.65GB
tabula-8b.Q6_K.gguf	Q6_K	6.14GB
tabula-8b.Q8_0.gguf	Q8_0	7.95GB

Original model description:

license: llama3 datasets: - jpgard/t4-full language: - en

This repository contains the TabuLa-8B (Tabular Llama-8B) model. TabuLa-8B is a foundation model for prediction (classification and binned regression) on tabular data.

TabuLa-8B is described in the paper "Large Scale Transfer Learning for Tabular Data via Language Modeling."

For more details on the model, see the paper, which includes a Model Card detailing the model architecture, training, and evaluation. TabuLa-8B was trained with rtfm, using the T4 dataset.

TabuLa-8B is built with Meta Llama 3.

Usage and Examples

You can load the model with transformers via

from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("mlfoundations/tabula-8b")
model = AutoModelForCausalLM.from_pretrained("mlfoundations/tabula-8b")

For more information on how to prepare data and run inference (including a demo notebook for performing inference on your data), see the examples in rtfm.

License and Terms of Use

TabuLa-8B is fine-tuned from the Llama-3 8B model. As a result, we release it under the Llama 3 license, and by using the model you agree to abide by the Llama 3 Community License Agreement and the Llama 3 Acceptable Use Policy.