StableLM Zephyr 3B: Complete Benchmark Performance Guide

other stablelm-zephyr-3b 2024-01-19 Stability AI Community License

In-depth analysis of StableLM Zephyr 3B performance on MMLU, HumanEval, GSM8K, MATH, BBH benchmarks, including pricing and use cases.

Key Specifications

Vendorother
Versionstablelm-zephyr-3b
Release Date2024-01-19
Context Window4096 tokens
Input Modalitiestext
Output Modalitiestext
LicenseStability AI Community License
Documentationhttps://huggingface.co/models

Benchmark Performance

BenchmarkScoreUnitEvaluated AtNotesSource
MMLU44.3%2024-01-195-shotview
HUMANEVAL47.1pass@12024-01-19—view
GSM8K36.2%2024-01-190-shot CoTview
MATH14.9%2024-01-190-shot CoTview
BBH43.9%2024-01-193-shot CoTview
GPQA21%2024-01-190-shotview
IFEVAL55.3%2024-01-19prompt_strictview
ARC82.1%2024-01-19challengeview
MUSR23.5%2024-01-190-shotview
WINOGRANDE71.6%2024-01-190-shotview

Pricing

TierPriceCurrency
Input$0.12 / MtokUSD
Output$0.12 / 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 Zephyr 3B

모델 개요

Stability AI StableLM Zephyr 3B 对话微调模型, 4K 上下文, 基于 StableLM 2 1.6B DPO 微调。

핵심 사양

공급업체버전출시일컨텍스트 창입력 모달리티출력 모달리티라이선스
Otherstablelm-zephyr-3b2024-01-194KtexttextStability AI Community License

벤치마크 성능

벤치마크점수단위비고
MMLU (Massive Multitask Language Understanding)44.3%5-shot
HumanEval47.1pass@1—
GSM8K (Grade School Math 8K)36.2%0-shot CoT
MATH14.9%0-shot CoT
BBH (BIG-Bench Hard)43.9%3-shot CoT
GPQA21.0%0-shot
IFEval55.3%prompt_strict
ARC82.1%challenge
MUSR23.5%0-shot
WinoGrande71.6%0-shot

가격

입력출력캐시 읽기캐시 쓰기
————

백만 토큰당

강점

  • 可靠的通用模型。

약점

  • MMLU 仅 44.3，知识推理偏弱。
  • HumanEval 47.1，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。

사용 사례

  • 通用对话与问答

참고문헌