ggml-org/llama.cpp

MiniCPM 2b model support?

Open

#5,276 opened on Feb 2, 2024

View on GitHub
 (26 comments) (8 reactions) (0 assignees)C++ (18,202 forks)batch import
enhancementgood first issue

Repository metrics

Stars
 (110,169 stars)
PR merge metrics
 (Avg merge 6d 8h) (389 merged PRs in 30d)

Description

Feature Description

Like Phi is supported, it would great to have this Mistral level 2b model ggufable.

Motivation

SOTA 2b model, a piece of art, read how they made it:

https://shengdinghu.notion.site/MiniCPM-Unveiling-the-Potential-of-End-side-Large-Language-Models-d4d3a8c426424654a4e80e42a711cb20

Contributor guide

Research direction
Study the MiniCPM model architecture and compare it with Phi to identify necessary changes. Then, write a conversion script in Python and add inference support in C++.
Tech stack
cpp
Domain
backend
Issue type
Feature
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
3
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
1-2 days
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
Active
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Clear
Prerequisites
C++Git
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
55