🚀 テキスト生成モデルに関する情報
このドキュメントでは、テキスト生成モデルに関する様々な情報を提供しています。データセット、サポート言語、パイプラインタグ、ウィジェットの例、モデルの評価結果などが含まれています。
📦 データセット
データセット名 |
bigscience/xP3 |
mc4 |
📄 ライセンス
このモデルは apache-2.0
ライセンスの下で提供されています。
🌐 サポート言語
- af, am, ar, az, be, bg, bn, ca, ceb, co, cs, cy, da, de, el, en, eo, es, et, eu, fa, fi, fil, fr, fy, ga, gd, gl, gu, ha, haw, hi, hmn, ht, hu, hy, ig, is, it, iw, ja, jv, ka, kk, km, kn, ko, ku, ky, la, lb, lo, lt, lv, mg, mi, mk, ml, mn, mr, ms, mt, my, ne, nl, 'no', ny, pa, pl, ps, pt, ro, ru, sd, si, sk, sl, sm, sn, so, sq, sr, st, su, sv, sw, ta, te, tg, th, tr, uk, und, ur, uz, vi, xh, yi, yo, zh, zu
🛠️ パイプラインタグ
👀 ウィジェットの例
例のタイトル |
入力テキスト |
zh-en sentiment |
一个传奇的开端,一个不灭的神话,这不仅仅是一部电影,而是作为一个走进新时代的标签,永远彪炳史册。Would you rate the previous review as positive, neutral or negative? |
zh-zh sentiment |
一个传奇的开端,一个不灭的神话,这不仅仅是一部电影,而是作为一个走进新时代的标签,永远彪炳史册。你认为这句话的立场是赞扬、中立还是批评? |
vi-en query |
Suggest at least five related search terms to "Mạng neural nhân tạo". |
fr-fr query |
Proposez au moins cinq mots clés concernant «Réseau de neurones artificiels». |
te-en qa |
Explain in a sentence in Telugu what is backpropagation in neural networks. |
en-en qa |
Why is the sky blue? |
es-en fable |
Write a fairy tale about a troll saving a princess from a dangerous dragon. The fairy tale is a masterpiece that has achieved praise worldwide and its moral is "Heroes Come in All Shapes and Sizes". Story (in Spanish): |
hi-en fable |
Write a fable about wood elves living in a forest that is suddenly invaded by ogres. The fable is a masterpiece that has achieved praise worldwide and its moral is "Violence is the last refuge of the incompetent". Fable (in Hindi): |
📊 モデル評価結果
mt0-xl モデル
タスクタイプ |
データセット名 |
データセット構成 |
分割 |
評価指標 |
値 |
Coreference resolution |
Winogrande XL (xl) |
xl |
validation |
Accuracy |
52.49 |
Coreference resolution |
XWinograd (en) |
en |
test |
Accuracy |
61.89 |
Coreference resolution |
XWinograd (fr) |
fr |
test |
Accuracy |
59.04 |
Coreference resolution |
XWinograd (jp) |
jp |
test |
Accuracy |
60.27 |
Coreference resolution |
XWinograd (pt) |
pt |
test |
Accuracy |
66.16 |
Coreference resolution |
XWinograd (ru) |
ru |
test |
Accuracy |
59.05 |
Coreference resolution |
XWinograd (zh) |
zh |
test |
Accuracy |
62.9 |
Natural language inference |
ANLI (r1) |
r1 |
validation |
Accuracy |
38.2 |
Natural language inference |
ANLI (r2) |
r2 |
validation |
Accuracy |
34.8 |
Natural language inference |
ANLI (r3) |
r3 |
validation |
Accuracy |
39 |
Natural language inference |
SuperGLUE (cb) |
cb |
validation |
Accuracy |
85.71 |
Natural language inference |
SuperGLUE (rte) |
rte |
validation |
Accuracy |
78.7 |
Natural language inference |
XNLI (ar) |
ar |
validation |
Accuracy |
51.85 |
Natural language inference |
XNLI (bg) |
bg |
validation |
Accuracy |
54.18 |
Natural language inference |
XNLI (de) |
de |
validation |
Accuracy |
54.78 |
Natural language inference |
XNLI (el) |
el |
validation |
Accuracy |
53.78 |
Natural language inference |
XNLI (en) |
en |
validation |
Accuracy |
56.83 |
Natural language inference |
XNLI (es) |
es |
validation |
Accuracy |
54.78 |
Natural language inference |
XNLI (fr) |
fr |
validation |
Accuracy |
54.22 |
Natural language inference |
XNLI (hi) |
hi |
validation |
Accuracy |
50.24 |
Natural language inference |
XNLI (ru) |
ru |
validation |
Accuracy |
53.09 |
Natural language inference |
XNLI (sw) |
sw |
validation |
Accuracy |
49.6 |
Natural language inference |
XNLI (th) |
th |
validation |
Accuracy |
52.13 |
Natural language inference |
XNLI (tr) |
tr |
validation |
Accuracy |
50.56 |
Natural language inference |
XNLI (ur) |
ur |
validation |
Accuracy |
47.91 |
Natural language inference |
XNLI (vi) |
vi |
validation |
Accuracy |
53.21 |
Natural language inference |
XNLI (zh) |
zh |
validation |
Accuracy |
50.64 |
Program synthesis |
HumanEval |
None |
test |
Pass@1 |
0 |
Program synthesis |
HumanEval |
None |
test |
Pass@10 |
0 |
Program synthesis |
HumanEval |
None |
test |
Pass@100 |
0 |
Sentence completion |
StoryCloze (2016) |
'2016' |
validation |
Accuracy |
79.1 |
Sentence completion |
SuperGLUE (copa) |
copa |
validation |
Accuracy |
72 |
Sentence completion |
XCOPA (et) |
et |
validation |
Accuracy |
70 |
Sentence completion |
XCOPA (ht) |
ht |
validation |
Accuracy |
66 |
Sentence completion |
XCOPA (id) |
id |
validation |
Accuracy |
71 |
Sentence completion |
XCOPA (it) |
it |
validation |
Accuracy |
70 |
Sentence completion |
XCOPA (qu) |
qu |
validation |
Accuracy |
56 |
Sentence completion |
XCOPA (sw) |
sw |
validation |
Accuracy |
53 |
Sentence completion |
XCOPA (ta) |
ta |
validation |
Accuracy |
64 |
Sentence completion |
XCOPA (th) |
th |
validation |
Accuracy |
60 |
Sentence completion |
XCOPA (tr) |
tr |
validation |
Accuracy |
58 |
Sentence completion |
XCOPA (vi) |
vi |
validation |
Accuracy |
68 |
Sentence completion |
XCOPA (zh) |
zh |
validation |
Accuracy |
65 |
Sentence completion |
XStoryCloze (ar) |
ar |
validation |
Accuracy |
70.09 |
Sentence completion |
XStoryCloze (es) |
es |
validation |
Accuracy |
77.17 |
Sentence completion |
XStoryCloze (eu) |
eu |
validation |
Accuracy |
69.03 |
Sentence completion |
XStoryCloze (hi) |
hi |
validation |
Accuracy |
71.08 |
Sentence completion |
XStoryCloze (id) |
id |
validation |
Accuracy |
75.71 |
Sentence completion |
XStoryCloze (my) |
my |
validation |
Accuracy |
65.65 |
Sentence completion |
XStoryCloze (ru) |
ru |
validation |
Accuracy |
74.85 |
Sentence completion |
XStoryCloze (sw) |
sw |
validation |
Accuracy |
71.14 |
Sentence completion |
XStoryCloze (te) |
te |
validation |
Accuracy |
68.89 |
Sentence completion |
XStoryCloze (zh) |
zh |
validation |
Accuracy |
74.85 |