Forge is a QLoRA fine-tune of Google’s Gemma 3 27B-IT base model, conditioned for structured code generation, multi-language debugging, and algorithmic problem solving across Python, JavaScript, Java, C++, C and SQL. This repository contains the Q4KM GGUF weights for local inference on consumer hardware. The unquantized bfloat16 merge is ~56 GB; Q4KM compresses it to ~16 GB, runnable on a single 24 GB GPU or with CPU offloading on 12 GB VRAM cards. EvalSpy repo link — a CLI that audits LLM eval pipelines for the exact bugs encountered building this model (0% HumanEval, 9% MBPP, 0 DebugBench samples). > Author is open to LLM engineering roles (India onsite / worldwide remote). Contact: kaustubhkubitkar@gmail.com (Note: The generation phase in the attached video is speed up 8x. Real-time inference on the 3060 took ~4 minutes.) this is the link to the video : https://youtu.be/3acwPjRmo74 Tested using llama.cpp with Q4KM quantization and partial GPU offloading. > DebugBench was included in the pipeline but contributed 0 training samples due to a > field-name mismatch (solution vs fixedcode) discovered during evaluation. Training > effectively ran on ~33 K samples from the first two…
Модальности:
Генерация текста
Области применения:
Генерация кода Диалог / чат
Языки программирования:
Python JavaScript Java C++
Задача: Генерация текста
Автор: KK9922
Теги: gguf, gemma-3, gemma-3-27b, code-generation, debugging, python, cpp, java
Лайков: 3 | Загрузок: 81
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
