LLM ReferenceLLM Reference

DeepSeek Math 7B Instruct

Open Source

Capabilities

VisionMultimodalReasoningFunction CallingTool UseStructured OutputsCode Execution

Benchmark Scores(4)

BenchmarkScoreVersionSource
Google-Proof Q&A49.2diamondOpen LLM Leaderboard
HellaSwag90.110-shotOpen LLM Leaderboard
HumanEval78.9pass@1Open LLM Leaderboard
Massive Multitask Language Understanding75.95-shotOpen LLM Leaderboard

Rankings

Specifications

Released2024-02-05
Parameters7B
ArchitectureDecoder Only
Specializationmath
Trainingfinetuning
Fine-tuninginstruct

Created by

Advancing artificial general intelligence (AGI).

Hangzhou, Zhejiang, China
Founded 2023
Website