Model card
Qwen2 72B.
Alibabaopen-weightUnknown paramsTransformer (decoder-only)
Qwen2 72B Instruct, released July 2024.
§ 02 · Benchmarks
Every benchmark Qwen2 72B has a recorded score for.
| # | Benchmark | Area · Task | Metric | Value | Rank | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | CNN/DailyMail | Natural Language Processing · Text Summarization | rouge-1 | 44.7% | #5 | 2024-07-15 | source ↗ |
| 02 | CNN/DailyMail | Natural Language Processing · Text Summarization | rouge-l | 41.8% | #5 | 2024-07-15 | source ↗ |
| 03 | CoNLL-2003 | Natural Language Processing · Named Entity Recognition | f1 | 90.2% | #5 | 2024-07-15 | source ↗ |
| 04 | SNLI | Natural Language Processing · Natural Language Inference | accuracy | 90.1% | #6 | 2024-07-15 | source ↗ |
| 05 | SuperGLUE | Natural Language Processing · Text classification | average-score | 85.4% | #7 | 2024-07-15 | source ↗ |
| 06 | SQuAD v2.0 | Natural Language Processing · Question Answering | f1 | 86.1% | #22 | 2024-07-15 | source ↗ |
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 03 · Strengths by area
Where Qwen2 72B actually performs.
§ 04 · Papers
1 paper with results for Qwen2 72B.
- 2024-07-15· Natural Language Processing· 6 results
Qwen2 Technical Report
§ 05 · Related models
Other Alibaba models scored on Codesota.
§ 06 · Sources & freshness
Where these numbers come from.
arxiv
6
results
6 of 6 rows marked verified.