StableLM 2 1.6B: Complete Benchmark Performance Guide

other stablelm-2-1-6b 2024-01-19 Stability AI Community License

In-depth analysis of StableLM 2 1.6B performance on MMLU, HumanEval, GSM8K, MATH, BBH benchmarks, including pricing and use cases.

Key Specifications

Vendorother
Versionstablelm-2-1-6b
Release Date2024-01-19
Context Window4096 tokens
Input Modalitiestext
Output Modalitiestext
LicenseStability AI Community License
Documentationhttps://huggingface.co/models

Benchmark Performance

BenchmarkScoreUnitEvaluated AtNotesSource
MMLU52.7%2024-01-195-shotview
HUMANEVAL37.3pass@12024-01-19—view
GSM8K43.5%2024-01-190-shot CoTview
MATH26.4%2024-01-190-shot CoTview
BBH40.7%2024-01-193-shot CoTview
GPQA15%2024-01-190-shotview
IFEVAL44.1%2024-01-19prompt_strictview
ARC77.7%2024-01-19challengeview
MUSR26.4%2024-01-190-shotview
WINOGRANDE70.3%2024-01-190-shotview

Pricing

TierPriceCurrency
Input$0.1 / MtokUSD
Output$0.1 / MtokUSD
Cache Read$0 / MtokUSD
Cache Write$0 / MtokUSD

Source: https://huggingface.co/models · as of 2024-01-19

Compliance

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

StableLM 2 1.6B

Visão geral do modelo

Stability AI StableLM 2 1.6B 轻量模型, 4K 上下文, 多语言训练, 适合移动设备部署。

Especificações principais

FornecedorVersãoData de lançamentoJanela de contextoModalidades de entradaModalidades de saídaLicença
Otherstablelm-2-1-6b2024-01-194KtexttextStability AI Community License

Desempenho em benchmarks

BenchmarkPontuaçãoUnidadeNotas
MMLU (Massive Multitask Language Understanding)52.7%5-shot
HumanEval37.3pass@1—
GSM8K (Grade School Math 8K)43.5%0-shot CoT
MATH26.4%0-shot CoT
BBH (BIG-Bench Hard)40.7%3-shot CoT
GPQA15.0%0-shot
IFEval44.1%prompt_strict
ARC77.7%challenge
MUSR26.4%0-shot
WinoGrande70.3%0-shot

Preços

EntradaSaídaLeitura de cacheEscrita de cache
————

por milhão de tokens

Pontos fortes

  • 可靠的通用模型。

Pontos fracos

  • MMLU 仅 52.7，知识推理偏弱。
  • HumanEval 37.3，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。

Casos de uso

  • 通用对话与问答

Referências