Key Specifications
| Vendor | other |
|---|
| Version | flan-t5-xxl |
|---|
| Release Date | 2022-12-07 |
|---|
| Context Window | 4096 tokens |
|---|
| Input Modalities | text |
|---|
| Output Modalities | text |
|---|
| License | Apache 2.0 |
|---|
| Documentation | https://huggingface.co/models |
|---|
Benchmark Performance
| Benchmark | Score | Unit | Evaluated At | Notes | Source |
|---|
| MMLU | 52 | % | 2022-12-07 | 5-shot | view |
| HUMANEVAL | 35.4 | pass@1 | 2022-12-07 | — | view |
| GSM8K | 35.2 | % | 2022-12-07 | 0-shot CoT | view |
| MATH | 21.4 | % | 2022-12-07 | 0-shot CoT | view |
| BBH | 60.5 | % | 2022-12-07 | 3-shot CoT | view |
| GPQA | 28.6 | % | 2022-12-07 | 0-shot | view |
| IFEVAL | 51.3 | % | 2022-12-07 | prompt_strict | view |
| ARC | 81.7 | % | 2022-12-07 | challenge | view |
| MUSR | 42.2 | % | 2022-12-07 | 0-shot | view |
| WINOGRANDE | 74.2 | % | 2022-12-07 | 0-shot | view |
Pricing
| Tier | Price | Currency |
|---|
| Input | $0.5 / Mtok | USD |
| Output | $0.5 / Mtok | USD |
| Cache Read | $0 / Mtok | USD |
| Cache Write | $0 / Mtok | USD |
Source:
https://huggingface.co/models
· as of 2022-12-07
Compliance
- Data Residency: self-host
- SOC2: ✗
- HIPAA: ✗
- GDPR: ✗
- ISO 27001: ✗
Flan-T5 XXL
Aperçu du modèle
Google Flan-T5 XXL 11B 指令微调模型, 4K 上下文, 多任务指令微调, 零样本能力突出。
Spécifications principales
| Fournisseur | Version | Date de sortie | Fenêtre de contexte | Modalités d’entrée | Modalités de sortie | Licence |
|---|
| Other | flan-t5-xxl | 2022-12-07 | 4K | text | text | Apache 2.0 |
| Benchmark | Score | Unité | Notes |
|---|
| MMLU (Massive Multitask Language Understanding) | 52.0 | % | 5-shot |
| HumanEval | 35.4 | pass@1 | — |
| GSM8K (Grade School Math 8K) | 35.2 | % | 0-shot CoT |
| MATH | 21.4 | % | 0-shot CoT |
| BBH (BIG-Bench Hard) | 60.5 | % | 3-shot CoT |
| GPQA | 28.6 | % | 0-shot |
| IFEval | 51.3 | % | prompt_strict |
| ARC | 81.7 | % | challenge |
| MUSR | 42.2 | % | 0-shot |
| WinoGrande | 74.2 | % | 0-shot |
Tarification
| Entrée | Sortie | Lecture cache | Écriture cache |
|---|
| — | — | — | — |
par million de jetons
Forces
Faiblesses
- MMLU 仅 52.0，知识推理偏弱。
- HumanEval 35.4，代码能力较弱。
- 闭源专有模型，不支持自托管。
- 上下文窗口 4K 偏小。
Cas d’usage
Références