MiniCPM-2B-SFT

Name: MiniCPM-2B-SFT
Author: ModelBest

Foundation modelMiniCPM-2B

MiniCPM-2B-SFT

Release date: 2024-02-01Updated: 2024-02-03Views: 599

Live demoGitHub Hugging Face Compare

Parameters

2.4B

Context length

Multilingual

Supported

Reasoning ability

No data

MiniCPM-2B-SFT is an AI model published by ModelBest, released on 2024-02-01, for Foundation model, with 2.4B parameters, and 2K context length, requiring about 10.9GB storage, with a 53.83 score on GSM8K.

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

MiniCPM-2B-SFT

Model basics

Reasoning traces

No data

Thinking modes

Thinking modes not supported

Context length

2K tokens

Max output length

No data

Model type

Foundation model

Modality (in / out)

No data

Release date

2024-02-01

Model file size

10.9GB

MoE architecture

Total params / Active params

2.4B / Not applicable

Knowledge cutoff

No data

MiniCPM-2B-SFT

Open source & experience

Code license

Apache 2.0

Weights license

- Commercial use permitted

GitHub repo

github.com/OpenBMB/MiniCPM

Hugging Face

huggingface.co/openbmb/MiniCPM-2B-sft-fp32

Live demo

N/A

MiniCPM-2B-SFT

Official resources

Paper

DataLearnerAI blog

N/A

MiniCPM-2B-SFT

API details

API speed

No data

No public API pricing yet.

MiniCPM-2B-SFT

Benchmark Results

MiniCPM-2B-SFT currently shows benchmark results led by HumanEval (51 / 101, score 50), GSM8K (42 / 70, score 53.83), MBPP (49 / 70, score 47.31). This page also consolidates core specs, context limits, and API pricing so you can evaluate the model from benchmark results and deployment constraints together.