Key Specifications

Vendorother
Versionhermes-3-llama-3-1-8b
Release Date2024-08-12
Context Window131072 tokens
Input Modalitiestext
Output Modalitiestext
LicenseLlama 3.1 Community License
Documentationhttps://huggingface.co/models

Benchmark Performance

BenchmarkScoreUnitEvaluated AtNotesSource
MMLU73.1%2024-08-125-shotview
HUMANEVAL67.1pass@12024-08-12view
GSM8K72.9%2024-08-120-shot CoTview
MATH25.5%2024-08-120-shot CoTview
BBH62.6%2024-08-123-shot CoTview
GPQA31.5%2024-08-120-shotview
IFEVAL60.7%2024-08-12prompt_strictview
ARC88.7%2024-08-12challengeview
MUSR38%2024-08-120-shotview
WINOGRANDE78.1%2024-08-120-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 2024-08-12

Compliance

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

Hermes 3 Llama 3.1 8B

모델 개요

NousResearch Hermes 3 Llama 3.1 8B 微调模型, 131K 上下文, 经济型开源模型, 适合本地部署。

핵심 사양

공급업체버전출시일컨텍스트 창입력 모달리티출력 모달리티라이선스
Otherhermes-3-llama-3-1-8b2024-08-12131KtexttextLlama 3.1 Community License

벤치마크 성능

벤치마크점수단위비고
MMLU (Massive Multitask Language Understanding)73.1%5-shot
HumanEval67.1pass@1
GSM8K (Grade School Math 8K)72.9%0-shot CoT
MATH25.5%0-shot CoT
BBH (BIG-Bench Hard)62.6%3-shot CoT
GPQA31.5%0-shot
IFEval60.7%prompt_strict
ARC88.7%challenge
MUSR38.0%0-shot
WinoGrande78.1%0-shot

가격

입력출력캐시 읽기캐시 쓰기

백만 토큰당

강점

  • 可靠的通用模型。

약점

  • 闭源专有模型,不支持自托管。

사용 사례

  • 通用对话与问答

참고문헌