This dataset is comprised of the LAMBADA test split as pre-processed by OpenAI (see relevant discussions here and here). It also contains machine translated versions of the split in German, Spanish, French, and Italian.
Dataset Card
By EleutherAI, published under mit, revision 900124bf3b82.
Dataset Description
- Repository: openai/gpt2
- Paper: Radford et al. Language Models are Unsupervised Multitask Learners
Dataset Summary
This dataset is comprised of the LAMBADA test split as pre-processed by OpenAI (see relevant discussions here and here). It also contains machine translated versions of the split in German, Spanish, French, and Italian.
LAMBADA is used to evaluate the capabilities of computational models for text understanding by means of a word prediction task. LAMBADA is a collection of narrative texts sharing the characteristic that human subjects are able to guess their last word if they are exposed to the whole text, but not if they only see the last sentence preceding the target word. To succeed on LAMBADA, computational models cannot simply rely on local context, but must be able to keep track of information in the broader discourse.
Languages
English, German, Spanish, French, and Italian.
Source Data
Structure
default 5,153 rows
| Split | Rows | Size |
|---|---|---|
| test | 5,153 | 1.7 MB |
de 5,153 rows
| Split | Rows | Size |
|---|---|---|
| test | 5,153 | 1.9 MB |
en 5,153 rows
| Split | Rows | Size |
|---|---|---|
| test | 5,153 | 1.7 MB |
es 5,153 rows
| Split | Rows | Size |
|---|---|---|
| test | 5,153 | 1.8 MB |
fr 5,153 rows
| Split | Rows | Size |
|---|---|---|
| test | 5,153 | 1.9 MB |
it 5,153 rows
| Split | Rows | Size |
|---|---|---|
| test | 5,153 | 1.8 MB |
Details
- Repository
- EleutherAI/lambada_openai
- Publisher
- EleutherAI
- Task category
- Not stated by the source
- Tags
- Not stated by the source
- Size category
- 1K<n<10K
- Languages
- de, en, es, fr, it
- Revision
- 900124bf3b8235c6daf21033af9948b3f07346c4
- Last updated
- 2025-07-10
Files
16 files, 18.8 MB in total.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| data/lambada_test.jsonl | Data | 1.8 MB | 4aa8d02cd17c |
| data/lambada_test_de.jsonl | Data | 2.0 MB | 51c6c1795894 |
| data/lambada_test_en.jsonl | Data | 1.8 MB | 4aa8d02cd17c |
| data/lambada_test_es.jsonl | Data | 1.9 MB | ffd760026c64 |
| data/lambada_test_fr.jsonl | Data | 2.0 MB | 941ec6a73dba |
| data/lambada_test_it.jsonl | Data | 1.9 MB | 866542377167 |
| de/test/de.parquet | Data | 1.3 MB | b229b3828eb8 |
| default/test/default.parquet | Data | 1.2 MB | 99d8a9e54cda |
| en/test/en.parquet | Data | 1.2 MB | 99d8a9e54cda |
| es/test/es.parquet | Data | 1.2 MB | 20f22fc14177 |
| fr/test/fr.parquet | Data | 1.3 MB | 1bdbedfcdbc9 |
| it/test/it.parquet | Data | 1.2 MB | f187d9036e68 |
| lambada_openai.txt | Data | 4.8 KB | — |
| translation_script.txt | Data | 1.7 KB | — |
| README.md | Documentation | 5.5 KB | — |
| .gitattributes | Repository | 2.7 KB | — |
License and Download
- License
- mit
- Access
- No access gate
Released by EleutherAI through its official repository on Hugging Face. Read the license.