Key Specifications

Vendorother
Versionwizardcoder-python-34b
Release Date2023-08-17
Context Window16384 tokens
Input Modalitiestext
Output Modalitiestext
LicenseLlama 2 Community License
Documentationhttps://huggingface.co/models

Benchmark Performance

BenchmarkScoreUnitEvaluated AtNotesSource
MMLU60%2023-08-175-shotview
HUMANEVAL79.8pass@12023-08-17view
GSM8K46.7%2023-08-170-shot CoTview
MATH40.6%2023-08-170-shot CoTview
BBH67.2%2023-08-173-shot CoTview
GPQA36.6%2023-08-170-shotview
IFEVAL53.8%2023-08-17prompt_strictview
ARC91.2%2023-08-17challengeview
MUSR53.1%2023-08-170-shotview
WINOGRANDE70.4%2023-08-170-shotview

Pricing

TierPriceCurrency
Input$0.5 / MtokUSD
Output$0.5 / MtokUSD
Cache Read$0 / MtokUSD
Cache Write$0 / MtokUSD

Source: https://huggingface.co/models · as of 2023-08-17

Compliance

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

Microsoft WizardCoder Python 34B

Aperçu du modèle

Microsoft WizardCoder Python 34B 代码模型, 16K 上下文, 基于 Code Llama 34B, Python 代码生成突出。

Spécifications principales

FournisseurVersionDate de sortieFenêtre de contexteModalités d’entréeModalités de sortieLicence
Otherwizardcoder-python-34b2023-08-1716KtexttextLlama 2 Community License

Performance aux benchmarks

BenchmarkScoreUnitéNotes
MMLU (Massive Multitask Language Understanding)60.0%5-shot
HumanEval79.8pass@1
GSM8K (Grade School Math 8K)46.7%0-shot CoT
MATH40.6%0-shot CoT
BBH (BIG-Bench Hard)67.2%3-shot CoT
GPQA36.6%0-shot
IFEval53.8%prompt_strict
ARC91.2%challenge
MUSR53.1%0-shot
WinoGrande70.4%0-shot

Tarification

EntréeSortieLecture cacheÉcriture cache

par million de jetons

Forces

  • 可靠的通用模型。

Faiblesses

  • 闭源专有模型,不支持自托管。
  • 上下文窗口 16K 偏小。

Cas d’usage

  • 代码生成与调试

Références