Quantization made by Richard Erkhov.

[Github](https://github.com/RichardErkhov)

[Discord](https://discord.gg/pvy7H8DZMG)

[Request more models](https://github.com/RichardErkhov/quant_request)


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](https://huggingface.co/RichardErkhov/mlfoundations_-_tabula-8b-gguf/blob/main/tabula-8b.Q2_K.gguf) | Q2_K | 2.96GB |
| [tabula-8b.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/mlfoundations_-_tabula-8b-gguf/blob/main/tabula-8b.IQ3_XS.gguf) | IQ3_XS | 3.28GB |
| [tabula-8b.IQ3_S.gguf](https://huggingface.co/RichardErkhov/mlfoundations_-_tabula-8b-gguf/blob/main/tabula-8b.IQ3_S.gguf) | IQ3_S | 3.43GB |
| [tabula-8b.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/mlfoundations_-_tabula-8b-gguf/blob/main/tabula-8b.Q3_K_S.gguf) | Q3_K_S | 3.41GB |
| [tabula-8b.IQ3_M.gguf](https://huggingface.co/RichardErkhov/mlfoundations_-_tabula-8b-gguf/blob/main/tabula-8b.IQ3_M.gguf) | IQ3_M | 3.52GB |
| [tabula-8b.Q3_K.gguf](https://huggingface.co/RichardErkhov/mlfoundations_-_tabula-8b-gguf/blob/main/tabula-8b.Q3_K.gguf) | Q3_K | 3.74GB |
| [tabula-8b.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/mlfoundations_-_tabula-8b-gguf/blob/main/tabula-8b.Q3_K_M.gguf) | Q3_K_M | 3.74GB |
| [tabula-8b.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/mlfoundations_-_tabula-8b-gguf/blob/main/tabula-8b.Q3_K_L.gguf) | Q3_K_L | 4.03GB |
| [tabula-8b.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/mlfoundations_-_tabula-8b-gguf/blob/main/tabula-8b.IQ4_XS.gguf) | IQ4_XS | 4.18GB |
| [tabula-8b.Q4_0.gguf](https://huggingface.co/RichardErkhov/mlfoundations_-_tabula-8b-gguf/blob/main/tabula-8b.Q4_0.gguf) | Q4_0 | 4.34GB |
| [tabula-8b.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/mlfoundations_-_tabula-8b-gguf/blob/main/tabula-8b.IQ4_NL.gguf) | IQ4_NL | 4.38GB |
| [tabula-8b.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/mlfoundations_-_tabula-8b-gguf/blob/main/tabula-8b.Q4_K_S.gguf) | Q4_K_S | 4.37GB |
| [tabula-8b.Q4_K.gguf](https://huggingface.co/RichardErkhov/mlfoundations_-_tabula-8b-gguf/blob/main/tabula-8b.Q4_K.gguf) | Q4_K | 4.58GB |
| [tabula-8b.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/mlfoundations_-_tabula-8b-gguf/blob/main/tabula-8b.Q4_K_M.gguf) | Q4_K_M | 4.58GB |
| [tabula-8b.Q4_1.gguf](https://huggingface.co/RichardErkhov/mlfoundations_-_tabula-8b-gguf/blob/main/tabula-8b.Q4_1.gguf) | Q4_1 | 4.78GB |
| [tabula-8b.Q5_0.gguf](https://huggingface.co/RichardErkhov/mlfoundations_-_tabula-8b-gguf/blob/main/tabula-8b.Q5_0.gguf) | Q5_0 | 5.21GB |
| [tabula-8b.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/mlfoundations_-_tabula-8b-gguf/blob/main/tabula-8b.Q5_K_S.gguf) | Q5_K_S | 5.21GB |
| [tabula-8b.Q5_K.gguf](https://huggingface.co/RichardErkhov/mlfoundations_-_tabula-8b-gguf/blob/main/tabula-8b.Q5_K.gguf) | Q5_K | 5.34GB |
| [tabula-8b.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/mlfoundations_-_tabula-8b-gguf/blob/main/tabula-8b.Q5_K_M.gguf) | Q5_K_M | 5.34GB |
| [tabula-8b.Q5_1.gguf](https://huggingface.co/RichardErkhov/mlfoundations_-_tabula-8b-gguf/blob/main/tabula-8b.Q5_1.gguf) | Q5_1 | 5.65GB |
| [tabula-8b.Q6_K.gguf](https://huggingface.co/RichardErkhov/mlfoundations_-_tabula-8b-gguf/blob/main/tabula-8b.Q6_K.gguf) | Q6_K | 6.14GB |
| [tabula-8b.Q8_0.gguf](https://huggingface.co/RichardErkhov/mlfoundations_-_tabula-8b-gguf/blob/main/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."](https://arxiv.org/abs/2406.12031)

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](https://github.com/mlfoundations/rtfm), 
using the [T4 dataset](https://huggingface.co/datasets/mlfoundations/t4-full).

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](https://github.com/mlfoundations/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](https://llama.meta.com/llama3/license/), 
and by using the model you agree to abide by the [Llama 3 Community License Agreement](https://llama.meta.com/llama3/license/) 
and the Llama 3 [Acceptable Use Policy](https://llama.meta.com/llama3/use-policy/).