Key Specifications

Vendorother
Versionopenchat-3-6-8b
Release Date2024-05-21
Context Window8192 tokens
Input Modalitiestext
Output Modalitiestext
LicenseApache 2.0
Documentationhttps://huggingface.co/models

Benchmark Performance

BenchmarkScoreUnitEvaluated AtNotesSource
MMLU69.2%2024-05-215-shotview
HUMANEVAL61.5pass@12024-05-21view
GSM8K51.8%2024-05-210-shot CoTview
MATH33.7%2024-05-210-shot CoTview
BBH71%2024-05-213-shot CoTview
GPQA30.3%2024-05-210-shotview
IFEVAL56.7%2024-05-21prompt_strictview
ARC89.2%2024-05-21challengeview
MUSR38.2%2024-05-210-shotview
WINOGRANDE74.5%2024-05-210-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 2024-05-21

Compliance

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

OpenChat 3.6 8B

모델 개요

OpenChat 3.6 8B 对话模型, 8K 上下文, 基于 Llama 3 8B 微调, 改进推理与编码能力。

핵심 사양

공급업체버전출시일컨텍스트 창입력 모달리티출력 모달리티라이선스
Otheropenchat-3-6-8b2024-05-218KtexttextApache 2.0

벤치마크 성능

벤치마크점수단위비고
MMLU (Massive Multitask Language Understanding)69.2%5-shot
HumanEval61.5pass@1
GSM8K (Grade School Math 8K)51.8%0-shot CoT
MATH33.7%0-shot CoT
BBH (BIG-Bench Hard)71.0%3-shot CoT
GPQA30.3%0-shot
IFEval56.7%prompt_strict
ARC89.2%challenge
MUSR38.2%0-shot
WinoGrande74.5%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。
  • 上下文窗口 8K 偏小。

사용 사례

  • 通用对话与问答

참고문헌