Key Specifications
| Vendor | other |
|---|
| Version | mpt-7b |
|---|
| Release Date | 2023-05-04 |
|---|
| Context Window | 2048 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 | 51.7 | % | 2023-05-04 | 5-shot | view |
| HUMANEVAL | 38.1 | pass@1 | 2023-05-04 | — | view |
| GSM8K | 44.6 | % | 2023-05-04 | 0-shot CoT | view |
| MATH | 18.4 | % | 2023-05-04 | 0-shot CoT | view |
| BBH | 59.9 | % | 2023-05-04 | 3-shot CoT | view |
| GPQA | 34.2 | % | 2023-05-04 | 0-shot | view |
| IFEVAL | 59.9 | % | 2023-05-04 | prompt_strict | view |
| ARC | 87.5 | % | 2023-05-04 | challenge | view |
| MUSR | 42.4 | % | 2023-05-04 | 0-shot | view |
| WINOGRANDE | 65.5 | % | 2023-05-04 | 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 2023-05-04
Compliance
- Data Residency: self-host
- SOC2: ✗
- HIPAA: ✗
- GDPR: ✗
- ISO 27001: ✗
MPT 7B
Modeloverzicht
MosaicML MPT 7B 经济型开源模型, 2K 上下文, 7B 参数, Apache 2.0 可商用, 适合本地部署。
Kernspecificaties
| Leverancier | Versie | Releasedatum | Contextvenster | Invoermodaliteiten | Uitvoermodaliteiten | Licentie |
|---|
| Other | mpt-7b | 2023-05-04 | 2K | text | text | Apache 2.0 |
Benchmarkprestaties
| Benchmark | Score | Eenheid | Notities |
|---|
| MMLU (Massive Multitask Language Understanding) | 51.7 | % | 5-shot |
| HumanEval | 38.1 | pass@1 | — |
| GSM8K (Grade School Math 8K) | 44.6 | % | 0-shot CoT |
| MATH | 18.4 | % | 0-shot CoT |
| BBH (BIG-Bench Hard) | 59.9 | % | 3-shot CoT |
| GPQA | 34.2 | % | 0-shot |
| IFEval | 59.9 | % | prompt_strict |
| ARC | 87.5 | % | challenge |
| MUSR | 42.4 | % | 0-shot |
| WinoGrande | 65.5 | % | 0-shot |
Prijzen
| Invoer | Uitvoer | Cache-lezen | Cache-schrijven |
|---|
| — | — | — | — |
per miljoen tokens
Sterktes
Zwaktes
- MMLU 仅 51.7，知识推理偏弱。
- HumanEval 38.1，代码能力较弱。
- 闭源专有模型，不支持自托管。
- 上下文窗口 2K 偏小。
Gebruiksscenario’s
Referenties