---
title: FELA LLM 1.5 code completion
colorFrom: indigo
colorTo: purple
sdk: gradio
sdk_version: 4.44.0
app_file: app.py
pinned: false
license: other
---

# FELA LLM 1.5 code completion

Type the code before your cursor (Prefix) and optionally the code after it (Suffix), and
the model writes the line that goes in between. It runs on a plain CPU with no GPU.

## How it works

The model reads your prefix and suffix, and when the suffix is present it uses the fill
in the middle layout so the completion fits between them. It writes one line at a time,
greedy by default, so the same prompt gives the same real output every time.

## What to expect

This is the final fill in the middle model. Single line patterns land well (imports,
obvious returns, boilerplate); multi line blocks and novel logic are outside what it is
built for. Every completion is a genuine forward of the model, never a lookup. For fast
production serving the same weights run int8 on the CPU native FELA server.