DataLearner logo
YA

YAYI2-30B

Foundation modelYAYI2

YAYI2-30B

Release date: 2023-12-22Updated: 2023-12-26Views: 660
Parameters
30B
Context length
4K
Multilingual
Supported
Reasoning ability
No data

YAYI2-30B is an AI model published by Wenge Research, released on 2023-12-22, for Foundation model, with 30B parameters, and 4K context length, requiring about 60GB storage, with a 80.90 score on C-Eval.

Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology

YAYI2-30B

Model basics

Reasoning traces
No data
Thinking modes
Thinking modes not supported
Context length
4K tokens
Max output length
No data
Model type
Foundation model
Modality (in / out)
No data
Release date
2023-12-22
Model file size
60GB
MoE architecture
No
Total params / Active params
30B / Not applicable
Knowledge cutoff
No data
YAYI2-30B

Open source & experience

Code license
Weights license
- Commercial license required
Live demo
N/A
YAYI2-30B

Official resources

Paper
DataLearnerAI blog
N/A
YAYI2-30B

API details

API speed
No data
No public API pricing yet.
YAYI2-30B

Benchmark Results

YAYI2-30B currently shows benchmark results led by AGIEval (3 / 28, score 62), C-Eval (15 / 48, score 80.90), MMLU (53 / 124, score 80.50). This page also consolidates core specs, context limits, and API pricing so you can evaluate the model from benchmark results and deployment constraints together.

Thinking

General Knowledge

2 evaluations
Benchmark / mode
Score
Rank/total
C-Eval
Standard Mode
80.90
15 / 48
MMLU
Standard Mode
80.50
53 / 124

Math and Reasoning

1 evaluations
Benchmark / mode
Score
Rank/total
GSM8K
Standard Mode
71.20
30 / 70

Coding and Software Engineer

2 evaluations
Benchmark / mode
Score
Rank/total
HumanEval
Standard Mode
53.10
80 / 140
MBPP
Standard Mode
45.80
78 / 96

General Evaluation

1 evaluations
Benchmark / mode
Score
Rank/total
AGIEval
Standard Mode
62
3 / 28
YAYI2-30B

Publisher

YAYI2-30B

Model Overview

YAYI2-30B is an AI model published by Wenge Research, released on 2023-12-22, for Foundation model, with 30B parameters, and 4K context length, requiring about 60GB storage, with a 80.90 score on C-Eval.

DataLearner on WeChat

Follow DataLearner on WeChat for AI model updates and research notes.

DataLearner WeChat QR code