Key Specifications
| Vendor | other |
|---|
| Version | phi-3-vision |
|---|
| Release Date | 2024-05-21 |
|---|
| Context Window | 4096 tokens |
|---|
| Input Modalities | text, image |
|---|
| Output Modalities | text |
|---|
| License | MIT |
|---|
| Documentation | https://huggingface.co/models |
|---|
Benchmark Performance
| Benchmark | Score | Unit | Evaluated At | Notes | Source |
|---|
| MMLU | 56.4 | % | 2024-05-21 | 5-shot | view |
| HUMANEVAL | 48.2 | pass@1 | 2024-05-21 | — | view |
| GSM8K | 30 | % | 2024-05-21 | 0-shot CoT | view |
| MATH | 24.3 | % | 2024-05-21 | 0-shot CoT | view |
| BBH | 40.1 | % | 2024-05-21 | 3-shot CoT | view |
| GPQA | 17.4 | % | 2024-05-21 | 0-shot | view |
| IFEVAL | 56.4 | % | 2024-05-21 | prompt_strict | view |
| ARC | 77.4 | % | 2024-05-21 | challenge | view |
| MUSR | 32.1 | % | 2024-05-21 | 0-shot | view |
| WINOGRANDE | 74.7 | % | 2024-05-21 | 0-shot | view |
Pricing
| Tier | Price | Currency |
|---|
| Input | $0.2 / Mtok | USD |
| Output | $0.2 / Mtok | USD |
| Cache Read | $0 / Mtok | USD |
| Cache Write | $0 / Mtok | USD |
Source:
https://huggingface.co/models
· as of 2024-05-21
Compliance
- Data Residency: self-host
- SOC2: ✗
- HIPAA: ✗
- GDPR: ✗
- ISO 27001: ✗
Phi-3 Vision
Aperçu du modèle
Microsoft Phi-3 Vision 4.2B 多模态模型, 4K 上下文, 支持图像理解, 在 4B 规模上多模态能力领先。
Spécifications principales
| Fournisseur | Version | Date de sortie | Fenêtre de contexte | Modalités d’entrée | Modalités de sortie | Licence |
|---|
| Other | phi-3-vision | 2024-05-21 | 4K | text, image | text | MIT |
| Benchmark | Score | Unité | Notes |
|---|
| MMLU (Massive Multitask Language Understanding) | 56.4 | % | 5-shot |
| HumanEval | 48.2 | pass@1 | — |
| GSM8K (Grade School Math 8K) | 30.0 | % | 0-shot CoT |
| MATH | 24.3 | % | 0-shot CoT |
| BBH (BIG-Bench Hard) | 40.1 | % | 3-shot CoT |
| GPQA | 17.4 | % | 0-shot |
| IFEval | 56.4 | % | prompt_strict |
| ARC | 77.4 | % | challenge |
| MUSR | 32.1 | % | 0-shot |
| WinoGrande | 74.7 | % | 0-shot |
Tarification
| Entrée | Sortie | Lecture cache | Écriture cache |
|---|
| — | — | — | — |
par million de jetons
Forces
Faiblesses
- MMLU 仅 56.4，知识推理偏弱。
- HumanEval 48.2，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