Key Specifications
| Vendor | mistral |
|---|
| Version | 7b-v0.1 |
|---|
| Release Date | 2023-09-27 |
|---|
| Context Window | 8192 tokens |
|---|
| Input Modalities | text |
|---|
| Output Modalities | text |
|---|
| License | Apache 2.0 |
|---|
| Documentation | https://docs.mistral.ai/ |
|---|
Benchmark Performance
| Benchmark | Score | Unit | Evaluated At | Notes | Source |
|---|
| MMLU | 68.4 | % | 2023-09-27 | 5-shot | view |
| HUMANEVAL | 56.4 | pass@1 | 2023-09-27 | — | view |
| GSM8K | 63.1 | % | 2023-09-27 | 0-shot CoT | view |
| MATH | 26.5 | % | 2023-09-27 | 0-shot CoT | view |
| BBH | 65.4 | % | 2023-09-27 | 3-shot CoT | view |
| GPQA | 25.3 | % | 2023-09-27 | 0-shot | view |
| IFEVAL | 58.9 | % | 2023-09-27 | prompt_strict | view |
| ARC | 88.7 | % | 2023-09-27 | challenge | view |
| MUSR | 37.4 | % | 2023-09-27 | 0-shot | view |
| WINOGRANDE | 79.6 | % | 2023-09-27 | 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://mistral.ai/technology/
· as of 2023-09-27
Compliance
- Data Residency: EU
- SOC2: ✓
- HIPAA: ✗
- GDPR: ✓
- ISO 27001: ✓
Mistral 7B v0.1
Przegląd modelu
Mistral 7B v0.1 首版开源模型, 8K 上下文, 7B 参数, 在所有 7B 模型中表现领先, Apache 2.0 可商用。
Podstawowe specyfikacje
| Dostawca | Wersja | Data wydania | Okno kontekstowe | Modalności wejściowe | Modalności wyjściowe | Licencja |
|---|
| Mistral | 7b-v0.1 | 2023-09-27 | 8K | text | text | Apache 2.0 |
Wydajność benchmarków
| Benchmark | Wynik | Jednostka | Uwagi |
|---|
| MMLU (Massive Multitask Language Understanding) | 68.4 | % | 5-shot |
| HumanEval | 56.4 | pass@1 | — |
| GSM8K (Grade School Math 8K) | 63.1 | % | 0-shot CoT |
| MATH | 26.5 | % | 0-shot CoT |
| BBH (BIG-Bench Hard) | 65.4 | % | 3-shot CoT |
| GPQA | 25.3 | % | 0-shot |
| IFEval | 58.9 | % | prompt_strict |
| ARC | 88.7 | % | challenge |
| MUSR | 37.4 | % | 0-shot |
| WinoGrande | 79.6 | % | 0-shot |
Ceny
| Wejście | Wyjście | Odczyt pamięci podręcznej | Zapis pamięci podręcznej |
|---|
| — | — | — | — |
za milion tokenów
Mocne strony
Słabe strony
- 闭源专有模型，不支持自托管。
- 上下文窗口 8K 偏小。
Przypadki użycia
Referencje