Code Generation LLM LoRA

ProviderRabinovich
Categorycode-generation
LicenseApache-2.0
Downloads2
Stars0

Overview

This LoRA adapter is specifically tuned for code generation tasks, designed to be layered atop a base LLM to enhance syntax accuracy and logical structuring across multiple programming languages. Unlike general-purpose models, this fine-tune focuses on reducing boilerplate hallucinations and improving the precision of function implementations. For developers, this means a more streamlined integration into IDE plugins or automated CI/CD pipelines where concise, runnable code is prioritized over conversational prose. It serves as a lightweight alternative to deploying a full-parameter coding model, offering a smaller memory footprint while maintaining high performance in specialized software engineering workflows.

Highlights

  • Optimized for precise, runnable code generation
  • Lightweight LoRA architecture reduces VRAM overhead
  • Apache-2.0 license ensures flexible commercial integration
  • Reduces hallucinations in complex logic implementations

Usage

Install
# Install Hugging Face transformers
pip install transformers torch
SDK Usage
# Load model with transformers
from transformers import AutoModel, AutoTokenizer

model = AutoModel.from_pretrained("Rabinovich/Code-Generation-LLM-LoRA")
tokenizer = AutoTokenizer.from_pretrained("Rabinovich/Code-Generation-LLM-LoRA")

Hugging Face Download

We recommend downloading the model via the Hugging Face CLI or Hub SDK.

Guidance：Before downloading, install huggingface_hub with:

Guidance 
pip install -U huggingface_hub

CLI Download

Download the full repository

Download the full repository 
huggingface-cli download Rabinovich/Code-Generation-LLM-LoRA

Download a single file to a local folder (e.g. config.json into ./dir)

Download a single file to a local folder (e.g. config.json into ./dir) 
huggingface-cli download Rabinovich/Code-Generation-LLM-LoRA config.json --local-dir ./dir

See the official docs for more CLI options

SDK Download

SDK Download 
# 模型下载
from huggingface_hub import snapshot_download
model_dir = snapshot_download('Rabinovich/Code-Generation-LLM-LoRA')

Git Download

Make sure git-lfs is installed first

Git Download 
git lfs install
git clone https://huggingface.co/Rabinovich/Code-Generation-LLM-LoRA

To skip LFS large-file downloads, use:

Skip LFS 
GIT_LFS_SKIP_SMUDGE=1 git clone https://huggingface.co/Rabinovich/Code-Generation-LLM-LoRA

Model files are hosted on the Hugging Face Hub — download directly via HF CLI / SDK / Git, not through this site.

PyTorch / Transformers Usage

Install Transformers

Install Transformers 
pip install -U transformers torch

Load the model and run inference

Load the model and run inference 
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained('Rabinovich/Code-Generation-LLM-LoRA')
tokenizer = AutoTokenizer.from_pretrained('Rabinovich/Code-Generation-LLM-LoRA')

Full Documentation

来源: HuggingFace

---
library_name: peft
---

Training procedure

Framework versions

  • PEFT 0.5.0
View official source
Join our Telegram