Hugging Face's logo

RichardErkhov
/
mlfoundations_-_tabula-8b-gguf

GGUF
Model card Files
xet
Community
RichardErkhov commited on
Commit
66f8ef2
·
verified ·
1 Parent(s): 30565a8

uploaded readme

Browse files
Files changed (1) hide show
  1. README.md +82 -0
README.md ADDED
@@ -0,0 +1,82 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Quantization made by Richard Erkhov.
2
+
3
+ [Github](https://github.com/RichardErkhov)
4
+
5
+ [Discord](https://discord.gg/pvy7H8DZMG)
6
+
7
+ [Request more models](https://github.com/RichardErkhov/quant_request)
8
+
9
+
10
+ tabula-8b - GGUF
11
+ - Model creator: https://huggingface.co/mlfoundations/
12
+ - Original model: https://huggingface.co/mlfoundations/tabula-8b/
13
+
14
+
15
+ | Name | Quant method | Size |
16
+ | ---- | ---- | ---- |
17
+ | [tabula-8b.Q2_K.gguf](https://huggingface.co/RichardErkhov/mlfoundations_-_tabula-8b-gguf/blob/main/tabula-8b.Q2_K.gguf) | Q2_K | 2.96GB |
18
+ | [tabula-8b.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/mlfoundations_-_tabula-8b-gguf/blob/main/tabula-8b.IQ3_XS.gguf) | IQ3_XS | 3.28GB |
19
+ | [tabula-8b.IQ3_S.gguf](https://huggingface.co/RichardErkhov/mlfoundations_-_tabula-8b-gguf/blob/main/tabula-8b.IQ3_S.gguf) | IQ3_S | 3.43GB |
20
+ | [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 |
21
+ | [tabula-8b.IQ3_M.gguf](https://huggingface.co/RichardErkhov/mlfoundations_-_tabula-8b-gguf/blob/main/tabula-8b.IQ3_M.gguf) | IQ3_M | 3.52GB |
22
+ | [tabula-8b.Q3_K.gguf](https://huggingface.co/RichardErkhov/mlfoundations_-_tabula-8b-gguf/blob/main/tabula-8b.Q3_K.gguf) | Q3_K | 3.74GB |
23
+ | [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 |
24
+ | [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 |
25
+ | [tabula-8b.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/mlfoundations_-_tabula-8b-gguf/blob/main/tabula-8b.IQ4_XS.gguf) | IQ4_XS | 4.18GB |
26
+ | [tabula-8b.Q4_0.gguf](https://huggingface.co/RichardErkhov/mlfoundations_-_tabula-8b-gguf/blob/main/tabula-8b.Q4_0.gguf) | Q4_0 | 4.34GB |
27
+ | [tabula-8b.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/mlfoundations_-_tabula-8b-gguf/blob/main/tabula-8b.IQ4_NL.gguf) | IQ4_NL | 4.38GB |
28
+ | [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 |
29
+ | [tabula-8b.Q4_K.gguf](https://huggingface.co/RichardErkhov/mlfoundations_-_tabula-8b-gguf/blob/main/tabula-8b.Q4_K.gguf) | Q4_K | 4.58GB |
30
+ | [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 |
31
+ | [tabula-8b.Q4_1.gguf](https://huggingface.co/RichardErkhov/mlfoundations_-_tabula-8b-gguf/blob/main/tabula-8b.Q4_1.gguf) | Q4_1 | 4.78GB |
32
+ | [tabula-8b.Q5_0.gguf](https://huggingface.co/RichardErkhov/mlfoundations_-_tabula-8b-gguf/blob/main/tabula-8b.Q5_0.gguf) | Q5_0 | 5.21GB |
33
+ | [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 |
34
+ | [tabula-8b.Q5_K.gguf](https://huggingface.co/RichardErkhov/mlfoundations_-_tabula-8b-gguf/blob/main/tabula-8b.Q5_K.gguf) | Q5_K | 5.34GB |
35
+ | [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 |
36
+ | [tabula-8b.Q5_1.gguf](https://huggingface.co/RichardErkhov/mlfoundations_-_tabula-8b-gguf/blob/main/tabula-8b.Q5_1.gguf) | Q5_1 | 5.65GB |
37
+ | [tabula-8b.Q6_K.gguf](https://huggingface.co/RichardErkhov/mlfoundations_-_tabula-8b-gguf/blob/main/tabula-8b.Q6_K.gguf) | Q6_K | 6.14GB |
38
+ | [tabula-8b.Q8_0.gguf](https://huggingface.co/RichardErkhov/mlfoundations_-_tabula-8b-gguf/blob/main/tabula-8b.Q8_0.gguf) | Q8_0 | 7.95GB |
39
+
40
+
41
+
42
+
43
+ Original model description:
44
+ ---
45
+ license: llama3
46
+ datasets:
47
+ - jpgard/t4-full
48
+ language:
49
+ - en
50
+ ---
51
+
52
+ This repository contains the TabuLa-8B (Tabular Llama-8B) model.
53
+ TabuLa-8B is a foundation model for prediction (classification and binned regression) on tabular data.
54
+
55
+ TabuLa-8B is described in the paper ["Large Scale Transfer Learning for Tabular Data via Language Modeling."](https://arxiv.org/abs/2406.12031)
56
+
57
+ For more details on the model, see the paper, which includes a Model Card detailing the model architecture, training, and evaluation.
58
+ TabuLa-8B was trained with [rtfm](https://github.com/mlfoundations/rtfm),
59
+ using the [T4 dataset](https://huggingface.co/datasets/mlfoundations/t4-full).
60
+
61
+ TabuLa-8B is built with Meta Llama 3.
62
+
63
+ # Usage and Examples
64
+
65
+ You can load the model with `transformers` via
66
+ ```
67
+ from transformers import AutoTokenizer, AutoModelForCausalLM
68
+
69
+ tokenizer = AutoTokenizer.from_pretrained("mlfoundations/tabula-8b")
70
+ model = AutoModelForCausalLM.from_pretrained("mlfoundations/tabula-8b")
71
+ ```
72
+
73
+ 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).
74
+
75
+ # License and Terms of Use
76
+
77
+ TabuLa-8B is fine-tuned from the Llama-3 8B model.
78
+ As a result, we release it under the [Llama 3 license](https://llama.meta.com/llama3/license/),
79
+ and by using the model you agree to abide by the [Llama 3 Community License Agreement](https://llama.meta.com/llama3/license/)
80
+ and the Llama 3 [Acceptable Use Policy](https://llama.meta.com/llama3/use-policy/).
81
+
82
+