Replit-finetuned-v1-3b

Name: Replit-finetuned-v1-3b
Author: Replit

基础大模型

Release date: 2023-04-26更新于: 2023-04-27 22:54:16.977471

Live demo

Parameters

27.0亿

Context length

Chinese support

Not supported

Reasoning ability

Replit-finetuned-v1-3b is an AI model published by Replit, released on 2023-04-26, for 基础大模型, with 27.0B parameters, and 2K tokens context length.

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

Replit-finetuned-v1-3b

Model basics

Reasoning traces

Not supported

Thinking modes

Thinking modes not supported

Context length

2K tokens

Max output length

No data

Model type

基础大模型

Release date

2023-04-26

Model file size

No data

MoE architecture

Total params / Active params

27.0B / N/A

Knowledge cutoff

No data

Replit-finetuned-v1-3b

Open source & experience

Code license

No data

Weights license

No data

GitHub repo

GitHub link unavailable

Hugging Face

Hugging Face link unavailable

Live demo

No live demo

Replit-finetuned-v1-3b

Official resources

Paper

No paper available

DataLearnerAI blog

No blog post yet

Replit-finetuned-v1-3b

API details

API speed

No data

No public API pricing yet.

Replit-finetuned-v1-3b

Benchmark Results

No benchmark data to show.

Replit-finetuned-v1-3b

Publisher

Replit

View publisher details

Replit-finetuned-v1-3b

Model Overview

Replit-finetuned-v1-3b是Replit开发的一个编程大模型，与Replit-code-v1-3b一同宣布。官方确定Replit-code-v1-3b会是一个开源的模型，但是没有明确说Replit-finetuned-v1-3b是否开源。

Replit-code-v1-3b模型： https://www.datalearner.com/ai-models/pretrained-models/replit-code-v1-3b

从官方提供的比较看，该模型与Replit-code-v1-3b可能一样，基于5250亿tokens的代码数据集微调得到，但是可能做了进一步的训练，其效果也是好于Replit-code-v1-3b。

其它信息暂未公布！

Foundation model

LLaMA

View details

DataLearner 官方微信

欢迎关注 DataLearner 官方微信，获得最新 AI 技术推送