Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,78 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language:
|
3 |
+
- en
|
4 |
+
- fr
|
5 |
+
- ro
|
6 |
+
- de
|
7 |
+
- multilingual
|
8 |
+
|
9 |
+
widget:
|
10 |
+
- text: "Translate to German: My name is Arthur"
|
11 |
+
example_title: "Translation"
|
12 |
+
- text: "Please answer to the following question. Who is going to be the next Ballon d'or?"
|
13 |
+
example_title: "Question Answering"
|
14 |
+
- text: "Q: Can Geoffrey Hinton have a conversation with George Washington? Give the rationale before answering."
|
15 |
+
example_title: "Logical reasoning"
|
16 |
+
- text: "Please answer the following question. What is the boiling point of Nitrogen?"
|
17 |
+
example_title: "Scientific knowledge"
|
18 |
+
- text: "Answer the following yes/no question. Can you write a whole Haiku in a single tweet?"
|
19 |
+
example_title: "Yes/no question"
|
20 |
+
- text: "Answer the following yes/no question by reasoning step-by-step. Can you write a whole Haiku in a single tweet?"
|
21 |
+
example_title: "Reasoning task"
|
22 |
+
- text: "Q: ( False or not False or False ) is? A: Let's think step by step"
|
23 |
+
example_title: "Boolean Expressions"
|
24 |
+
- text: "The square root of x is the cube root of y. What is y to the power of 2, if x = 4?"
|
25 |
+
example_title: "Math reasoning"
|
26 |
+
- text: "Premise: At my age you will probably have learnt one lesson. Hypothesis: It's not certain how many lessons you'll learn by your thirties. Does the premise entail the hypothesis?"
|
27 |
+
example_title: "Premise and hypothesis"
|
28 |
+
|
29 |
+
tags:
|
30 |
+
- text2text-generation
|
31 |
+
|
32 |
+
datasets:
|
33 |
+
- svakulenk0/qrecc
|
34 |
+
- taskmaster2
|
35 |
+
- djaym7/wiki_dialog
|
36 |
+
- deepmind/code_contests
|
37 |
+
- lambada
|
38 |
+
- gsm8k
|
39 |
+
- aqua_rat
|
40 |
+
- esnli
|
41 |
+
- quasc
|
42 |
+
- qed
|
43 |
+
|
44 |
+
|
45 |
+
license: apache-2.0
|
46 |
+
---
|
47 |
+
|
48 |
+
# Model Card for FLAN-T5 XL
|
49 |
+
|
50 |
+
<img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/model_doc/flan2_architecture.jpg"
|
51 |
+
alt="drawing" width="600"/>
|
52 |
+
|
53 |
+
# Table of Contents
|
54 |
+
|
55 |
+
0. [TL;DR](#TL;DR)
|
56 |
+
1. [Model Details](#model-details)
|
57 |
+
2. [Usage](#usage)
|
58 |
+
3. [Uses](#uses)
|
59 |
+
4. [Bias, Risks, and Limitations](#bias-risks-and-limitations)
|
60 |
+
5. [Training Details](#training-details)
|
61 |
+
6. [Evaluation](#evaluation)
|
62 |
+
7. [Environmental Impact](#environmental-impact)
|
63 |
+
8. [Citation](#citation)
|
64 |
+
|
65 |
+
# TL;DR
|
66 |
+
|
67 |
+
If you already know T5, FLAN-T5 is just better at everything. For the same number of parameters, these models have been fine-tuned on more than 1000 additional tasks covering also more languages.
|
68 |
+
As mentioned in the first few lines of the abstract :
|
69 |
+
> Flan-PaLM 540B achieves state-of-the-art performance on several benchmarks, such as 75.2% on five-shot MMLU. We also publicly release Flan-T5 checkpoints,1 which achieve strong few-shot performance even compared to much larger models, such as PaLM 62B. Overall, instruction finetuning is a general method for improving the performance and usability of pretrained language models.
|
70 |
+
|
71 |
+
**Disclaimer**: Content from **this** model card has been written by the Hugging Face team, and parts of it were copy pasted from the [T5 model card](https://huggingface.co/t5-large).
|
72 |
+
|
73 |
+
# Model Details
|
74 |
+
|
75 |
+
## Model Description
|
76 |
+
|
77 |
+
|
78 |
+
The detail are in the original [google/flan-t5-xl](https://huggingface.co/google/flan-t5-xl)
|