Llemma 7B: Complete Benchmark Performance Guide

other llemma-7b 2023-10-17 Apache 2.0

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

Key Specifications

Vendorother
Versionllemma-7b
Release Date2023-10-17
Context Window4096 tokens
Input Modalitiestext
Output Modalitiestext
LicenseApache 2.0
Documentationhttps://huggingface.co/models

Benchmark Performance

BenchmarkScoreUnitEvaluated AtNotesSource
MMLU66%2023-10-175-shotview
HUMANEVAL64.2pass@12023-10-17—view
GSM8K84.9%2023-10-170-shot CoTview
MATH47.5%2023-10-170-shot CoTview
BBH73.1%2023-10-173-shot CoTview
GPQA37.4%2023-10-170-shotview
IFEVAL52.9%2023-10-17prompt_strictview
ARC87.4%2023-10-17challengeview
MUSR42.6%2023-10-170-shotview
WINOGRANDE70.8%2023-10-170-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 2023-10-17

Compliance

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

Llemma 7B

모델 개요

TheBloke Llemma 7B 数学专用模型, 4K 上下文, 基于 Code Llama 7B 继续训练, 数学推理能力突出。

핵심 사양

공급업체버전출시일컨텍스트 창입력 모달리티출력 모달리티라이선스
Otherllemma-7b2023-10-174KtexttextApache 2.0

벤치마크 성능

벤치마크점수단위비고
MMLU (Massive Multitask Language Understanding)66.0%5-shot
HumanEval64.2pass@1—
GSM8K (Grade School Math 8K)84.9%0-shot CoT
MATH47.5%0-shot CoT
BBH (BIG-Bench Hard)73.1%3-shot CoT
GPQA37.4%0-shot
IFEval52.9%prompt_strict
ARC87.4%challenge
MUSR42.6%0-shot
WinoGrande70.8%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 4K 偏小。

사용 사례

  • 通用对话与问答

참고문헌