ggml-org/llama.cpp

Test replit-code-v1-3b model

Open

#1,299 opened on May 3, 2023

View on GitHubContributor guide
 (7 comments) (0 reactions) (0 assignees)C++ (21,737 forks)batch import
help wantedmodel

Repository metrics

Stars
 (124,043 stars)
PR merge metrics
 (Avg merge 6d 8h) (389 merged PRs in 30d)

Description

Replit recently trained a 3B parameter Llama-style code model with some very promising results. Weights have been released here

Contributor guide

Research direction
Examine how existing models like CodeLlama are loaded in llama.cpp. Understand the model architecture of replit code v1-3b and adapt the weight loading and inference code accordingly.
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
GitC++
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
50