Key Specifications

Vendorcohere
Versionr7b
Release Date2024-08-13
Context Window128000 tokens
Input Modalitiestext
Output Modalitiestext
LicenseCC-BY-NC-4.0
Documentationhttps://docs.cohere.com/docs

Benchmark Performance

BenchmarkScoreUnitEvaluated AtNotesSource
MMLU64.9%2024-08-135-shotview
HUMANEVAL50.1pass@12024-08-13view
GSM8K69.7%2024-08-130-shot CoTview
MATH40.6%2024-08-130-shot CoTview
BBH66.1%2024-08-133-shot CoTview
GPQA30.9%2024-08-130-shotview
IFEVAL67.2%2024-08-13prompt_strictview
ARC90.7%2024-08-13challengeview
MUSR47%2024-08-130-shotview
WINOGRANDE74.1%2024-08-130-shotview

Pricing

TierPriceCurrency
Input$0.0375 / MtokUSD
Output$0.0375 / MtokUSD
Cache Read$0 / MtokUSD
Cache Write$0 / MtokUSD

Source: https://cohere.com/pricing · as of 2024-08-13

Compliance

  • Data Residency: US
  • SOC2: ✓
  • HIPAA: ✗
  • GDPR: ✓
  • ISO 27001: ✓

Command R7B

Modellübersicht

Cohere Command R7B 轻量开源模型, 128K 上下文, 7B 参数, 为 RAG 与工具调用优化, 适合边缘部署。

Kernspezifikationen

AnbieterVersionVeröffentlichungsdatumKontextfensterEingabemodalitätenAusgabemodalitätenLizenz
Coherer7b2024-08-13128KtexttextCC-BY-NC-4.0

Benchmark-Leistung

BenchmarkErgebnisEinheitNotizen
MMLU (Massive Multitask Language Understanding)64.9%5-shot
HumanEval50.1pass@1
GSM8K (Grade School Math 8K)69.7%0-shot CoT
MATH40.6%0-shot CoT
BBH (BIG-Bench Hard)66.1%3-shot CoT
GPQA30.9%0-shot
IFEval67.2%prompt_strict
ARC90.7%challenge
MUSR47.0%0-shot
WinoGrande74.1%0-shot

Preise

EingabeAusgabeCache-LesenCache-Schreiben

pro Million Token

Stärken

  • 可靠的通用模型。

Schwächen

  • 闭源专有模型,不支持自托管。

Anwendungsfälle

  • 通用对话与问答

Referenzen