Key Specifications
| Vendor | other |
|---|
| Version | yi-1-5-9b |
|---|
| Release Date | 2024-05-13 |
|---|
| 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 | 67.8 | % | 2024-05-13 | 5-shot | view |
| HUMANEVAL | 57.3 | pass@1 | 2024-05-13 | — | view |
| GSM8K | 72.8 | % | 2024-05-13 | 0-shot CoT | view |
| MATH | 34.1 | % | 2024-05-13 | 0-shot CoT | view |
| BBH | 65.3 | % | 2024-05-13 | 3-shot CoT | view |
| GPQA | 38 | % | 2024-05-13 | 0-shot | view |
| IFEVAL | 65.4 | % | 2024-05-13 | prompt_strict | view |
| ARC | 87.8 | % | 2024-05-13 | challenge | view |
| MUSR | 46.4 | % | 2024-05-13 | 0-shot | view |
| WINOGRANDE | 76.6 | % | 2024-05-13 | 0-shot | view |
Pricing
| Tier | Price | Currency |
|---|
| Input | $0.18 / Mtok | USD |
| Output | $0.18 / Mtok | USD |
| Cache Read | $0 / Mtok | USD |
| Cache Write | $0 / Mtok | USD |
Source:
https://huggingface.co/models
· as of 2024-05-13
Compliance
- Data Residency: self-host
- SOC2: ✗
- HIPAA: ✗
- GDPR: ✗
- ISO 27001: ✗
Yi 1.5 9B
Modellübersicht
01.AI Yi 1.5 9B 经济型开源模型, 4K 上下文, 9B 参数, 性能超越 Llama 2 13B, 适合本地部署。
Kernspezifikationen
| Anbieter | Version | Veröffentlichungsdatum | Kontextfenster | Eingabemodalitäten | Ausgabemodalitäten | Lizenz |
|---|
| Other | yi-1-5-9b | 2024-05-13 | 4K | text | text | Apache 2.0 |
Benchmark-Leistung
| Benchmark | Ergebnis | Einheit | Notizen |
|---|
| MMLU (Massive Multitask Language Understanding) | 67.8 | % | 5-shot |
| HumanEval | 57.3 | pass@1 | — |
| GSM8K (Grade School Math 8K) | 72.8 | % | 0-shot CoT |
| MATH | 34.1 | % | 0-shot CoT |
| BBH (BIG-Bench Hard) | 65.3 | % | 3-shot CoT |
| GPQA | 38.0 | % | 0-shot |
| IFEval | 65.4 | % | prompt_strict |
| ARC | 87.8 | % | challenge |
| MUSR | 46.4 | % | 0-shot |
| WinoGrande | 76.6 | % | 0-shot |
Preise
| Eingabe | Ausgabe | Cache-Lesen | Cache-Schreiben |
|---|
| — | — | — | — |
pro Million Token
Stärken
Schwächen
- 闭源专有模型，不支持自托管。
- 上下文窗口 4K 偏小。
Anwendungsfälle
Referenzen