Microsoft WizardLM 2 7B: Complete Benchmark Performance Guide

other wizardlm-2-7b 2024-04-15 Llama 3 Community License

In-depth analysis of Microsoft WizardLM 2 7B performance on MMLU, HumanEval, GSM8K, MATH, BBH benchmarks, including pricing and use cases.

Key Specifications

Vendorother
Versionwizardlm-2-7b
Release Date2024-04-15
Context Window32768 tokens
Input Modalitiestext
Output Modalitiestext
LicenseLlama 3 Community License
Documentationhttps://huggingface.co/models

Benchmark Performance

BenchmarkScoreUnitEvaluated AtNotesSource
MMLU65.7%2024-04-155-shotview
HUMANEVAL68.6pass@12024-04-15—view
GSM8K58.5%2024-04-150-shot CoTview
MATH30.5%2024-04-150-shot CoTview
BBH69.4%2024-04-153-shot CoTview
GPQA26.1%2024-04-150-shotview
IFEVAL56.9%2024-04-15prompt_strictview
ARC85.6%2024-04-15challengeview
MUSR49.3%2024-04-150-shotview
WINOGRANDE76.8%2024-04-150-shotview

Pricing

TierPriceCurrency
Input$0.18 / MtokUSD
Output$0.18 / MtokUSD
Cache Read$0 / MtokUSD
Cache Write$0 / MtokUSD

Source: https://huggingface.co/models · as of 2024-04-15

Compliance

  • Data Residency: self-host
  • SOC2: ✗
  • HIPAA: ✗
  • GDPR: ✗
  • ISO 27001: ✗

Microsoft WizardLM 2 7B

Modeloverzicht

Microsoft WizardLM 2 7B 经济型微调模型, 32K 上下文, 基于 Llama 3 7B, 改进指令遵循能力。

Kernspecificaties

LeverancierVersieReleasedatumContextvensterInvoermodaliteitenUitvoermodaliteitenLicentie
Otherwizardlm-2-7b2024-04-1532KtexttextLlama 3 Community License

Benchmarkprestaties

BenchmarkScoreEenheidNotities
MMLU (Massive Multitask Language Understanding)65.7%5-shot
HumanEval68.6pass@1—
GSM8K (Grade School Math 8K)58.5%0-shot CoT
MATH30.5%0-shot CoT
BBH (BIG-Bench Hard)69.4%3-shot CoT
GPQA26.1%0-shot
IFEval56.9%prompt_strict
ARC85.6%challenge
MUSR49.3%0-shot
WinoGrande76.8%0-shot

Prijzen

InvoerUitvoerCache-lezenCache-schrijven
————

per miljoen tokens

Sterktes

  • 可靠的通用模型。

Zwaktes

  • 闭源专有模型，不支持自托管。

Gebruiksscenario’s

  • 通用对话与问答

Referenties