Trending repositories for topic lora

Unified Efficient Fine-Tuning of 100+ LLMs (ACL 2024)

Finetune Llama 3.3, Mistral, Phi, Qwen 2.5 & Gemma LLMs 2-5x faster with 70% less memory

《开源大模型食用指南》针对中国宝宝量身打造的基于Linux环境快速微调（全参数/Lora）、部署国内外开源大模型（LLM）/多模态大模型（MLLM）教程

🧑‍🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), ga...

Use PEFT or Full-parameter to finetune 400+ LLMs (Qwen2.5, Llama3.2, GLM4, Internlm2.5, Yi1.5, Mistral, Baichuan2, DeepSeek, ...) or 100+ MLLMs (Qwen2-VL, Qwen2-Audio, Llama3.2-Vision, Llava, InternVL...

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

中文LLaMA&Alpaca大语言模型+本地CPU/GPU训练部署 (Chinese LLaMA & Alpaca LLMs)

Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"

Meshtastic device firmware

OneTrainer is a one-stop solution for all your stable diffusion training needs.

SD-Trainer. LoRA & Dreambooth training scripts & GUI use kohya-ss's trainer, for diffusion model.

AirLLM 70B inference with single 4GB GPU

Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs

Large-scale LLM inference engine

LLM Finetuning with peft

A toolbox for deep learning model deployment using C++ YoloX | YoloV7 | YoloV8 | Gan | OCR | MobileVit | Scrfd | MobileSAM | StableDiffusion

The cryptography-based networking stack for building unstoppable networks with LoRa, Packet Radio, WiFi and everything in between.

ESP32/ESP8285-based High-Performance Radio Link for RC applications

Firefly: 大模型训练工具，支持训练Qwen2.5、Qwen2、Yi1.5、Phi-3、Llama3、Gemma、MiniCPM、Yi、Deepseek、Orion、Xverse、Mixtral-8x7B、Zephyr、Mistral、Baichuan2、Llma2、Llama、Qwen、Baichuan、ChatGLM2、InternLM、Ziya2、Vicuna、Bloom等大模型

BELLE: Be Everyone's Large Language model Engine（开源中文对话大模型）

End to End Generative AI Industry Projects on LLM Models with Deployment_Awesome LLM Projects

📚 Text Classification with LoRA (Low-Rank Adaptation) of Language Models - Efficiently fine-tune large language models for text classification tasks using the Stanford Sentiment Treebank (SST-2) data...

A toolbox for deep learning model deployment using C++ YoloX | YoloV7 | YoloV8 | Gan | OCR | MobileVit | Scrfd | MobileSAM | StableDiffusion

《开源大模型食用指南》针对中国宝宝量身打造的基于Linux环境快速微调（全参数/Lora）、部署国内外开源大模型（LLM）/多模态大模型（MLLM）教程

Use PEFT or Full-parameter to finetune 400+ LLMs (Qwen2.5, Llama3.2, GLM4, Internlm2.5, Yi1.5, Mistral, Baichuan2, DeepSeek, ...) or 100+ MLLMs (Qwen2-VL, Qwen2-Audio, Llama3.2-Vision, Llava, InternVL...

Finetune Llama 3.3, Mistral, Phi, Qwen 2.5 & Gemma LLMs 2-5x faster with 70% less memory

OneTrainer is a one-stop solution for all your stable diffusion training needs.

Unified Efficient Fine-Tuning of 100+ LLMs (ACL 2024)

Large-scale LLM inference engine

AutoAudit—— the LLM for Cyber Security 网络安全大语言模型

Meshtastic device firmware

ChirpStack open-source LoRaWAN Network Server

Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs

LLM Finetuning with peft

A microframework on top of PyTorch with first-class citizen APIs for foundation model adaptation

Toolkit for fine-tuning, ablating and unit-testing open-source LLMs.

LXMF client for Android, Linux and macOS allowing you to communicate with people or LXMF-compatible systems over Reticulum networks using LoRa, Packet Radio, WiFi, I2P, or anything else Reticulum supp...

The cryptography-based networking stack for building unstoppable networks with LoRa, Packet Radio, WiFi and everything in between.

SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

Unified Efficient Fine-Tuning of 100+ LLMs (ACL 2024)

Finetune Llama 3.3, Mistral, Phi, Qwen 2.5 & Gemma LLMs 2-5x faster with 70% less memory

《开源大模型食用指南》针对中国宝宝量身打造的基于Linux环境快速微调（全参数/Lora）、部署国内外开源大模型（LLM）/多模态大模型（MLLM）教程

🧑‍🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), ga...

Use PEFT or Full-parameter to finetune 400+ LLMs (Qwen2.5, Llama3.2, GLM4, Internlm2.5, Yi1.5, Mistral, Baichuan2, DeepSeek, ...) or 100+ MLLMs (Qwen2-VL, Qwen2-Audio, Llama3.2-Vision, Llava, InternVL...

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

中文LLaMA&Alpaca大语言模型+本地CPU/GPU训练部署 (Chinese LLaMA & Alpaca LLMs)

Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"

Meshtastic device firmware

SD-Trainer. LoRA & Dreambooth training scripts & GUI use kohya-ss's trainer, for diffusion model.

LLM Finetuning with peft

OneTrainer is a one-stop solution for all your stable diffusion training needs.

SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models

The cryptography-based networking stack for building unstoppable networks with LoRa, Packet Radio, WiFi and everything in between.

Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs

ESP32/ESP8285-based High-Performance Radio Link for RC applications

Firefly: 大模型训练工具，支持训练Qwen2.5、Qwen2、Yi1.5、Phi-3、Llama3、Gemma、MiniCPM、Yi、Deepseek、Orion、Xverse、Mixtral-8x7B、Zephyr、Mistral、Baichuan2、Llma2、Llama、Qwen、Baichuan、ChatGLM2、InternLM、Ziya2、Vicuna、Bloom等大模型

A toolbox for deep learning model deployment using C++ YoloX | YoloV7 | YoloV8 | Gan | OCR | MobileVit | Scrfd | MobileSAM | StableDiffusion

AirLLM 70B inference with single 4GB GPU

Large-scale LLM inference engine

Consistency Distillation with Target Timestep Selection and Decoupled Guidance

📚 Text Classification with LoRA (Low-Rank Adaptation) of Language Models - Efficiently fine-tune large language models for text classification tasks using the Stanford Sentiment Treebank (SST-2) data...

A generalized framework for subspace tuning methods in parameter efficient fine-tuning.

LoRa trainer for SDXL and SD15

End to End Generative AI Industry Projects on LLM Models with Deployment_Awesome LLM Projects

SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models

LLaVA-NeXT-Image-Llama3-Lora, Modified from https://github.com/arielnlee/LLaVA-1.6-ft

Fine-Tune Whisper with Transformers and PEFT

Python library for basic transmitting and receiving data using LoRa and FSK modem

A toolbox for deep learning model deployment using C++ YoloX | YoloV7 | YoloV8 | Gan | OCR | MobileVit | Scrfd | MobileSAM | StableDiffusion

Arduino LoRa EBYTE E220 LLCC68 device library complete and tested with Arduino, esp8266, esp32, STM32 and Raspberry Pi Pico (rp2040 boards)..

Emotion text classification using Llama3-8b with LoRA and FlashAttention. Based on LLaMA-Factory.

Use PEFT or Full-parameter to finetune 400+ LLMs (Qwen2.5, Llama3.2, GLM4, Internlm2.5, Yi1.5, Mistral, Baichuan2, DeepSeek, ...) or 100+ MLLMs (Qwen2-VL, Qwen2-Audio, Llama3.2-Vision, Llava, InternVL...

《开源大模型食用指南》针对中国宝宝量身打造的基于Linux环境快速微调（全参数/Lora）、部署国内外开源大模型（LLM）/多模态大模型（MLLM）教程

对llama3进行全参微调、lora微调以及qlora微调。

X-LoRA: Mixture of LoRA Experts

Realtime web UI to run against a Meshtastic regional or private mesh network.

LXMF client for Android, Linux and macOS allowing you to communicate with people or LXMF-compatible systems over Reticulum networks using LoRa, Packet Radio, WiFi, I2P, or anything else Reticulum supp...

Finetune Llama 3.3, Mistral, Phi, Qwen 2.5 & Gemma LLMs 2-5x faster with 70% less memory

A simple mesh network communications app powered by the Reticulum Network Stack.

Unified Efficient Fine-Tuning of 100+ LLMs (ACL 2024)

Finetune Llama 3.3, Mistral, Phi, Qwen 2.5 & Gemma LLMs 2-5x faster with 70% less memory

🧑‍🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), ga...

《开源大模型食用指南》针对中国宝宝量身打造的基于Linux环境快速微调（全参数/Lora）、部署国内外开源大模型（LLM）/多模态大模型（MLLM）教程

Use PEFT or Full-parameter to finetune 400+ LLMs (Qwen2.5, Llama3.2, GLM4, Internlm2.5, Yi1.5, Mistral, Baichuan2, DeepSeek, ...) or 100+ MLLMs (Qwen2-VL, Qwen2-Audio, Llama3.2-Vision, Llava, InternVL...

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models

Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"

Meshtastic device firmware

中文LLaMA&Alpaca大语言模型+本地CPU/GPU训练部署 (Chinese LLaMA & Alpaca LLMs)

AirLLM 70B inference with single 4GB GPU

SD-Trainer. LoRA & Dreambooth training scripts & GUI use kohya-ss's trainer, for diffusion model.

Firefly: 大模型训练工具，支持训练Qwen2.5、Qwen2、Yi1.5、Phi-3、Llama3、Gemma、MiniCPM、Yi、Deepseek、Orion、Xverse、Mixtral-8x7B、Zephyr、Mistral、Baichuan2、Llma2、Llama、Qwen、Baichuan、ChatGLM2、InternLM、Ziya2、Vicuna、Bloom等大模型

LLM Finetuning with peft

OneTrainer is a one-stop solution for all your stable diffusion training needs.

Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs

ESP32/ESP8285-based High-Performance Radio Link for RC applications

BELLE: Be Everyone's Large Language model Engine（开源中文对话大模型）

Large-scale LLM inference engine

The cryptography-based networking stack for building unstoppable networks with LoRa, Packet Radio, WiFi and everything in between.

SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models

大模型/LLM推理和部署理论与实践

Settings for AI Training

Codebase for "CtrLoRA: An Extensible and Efficient Framework for Controllable Image Generation"

Monitor your meshtastic network with Meshtastic Prometheus exporter

End to End Generative AI Industry Projects on LLM Models with Deployment_Awesome LLM Projects

A generalized framework for subspace tuning methods in parameter efficient fine-tuning.

Realtime web UI to run against a Meshtastic regional or private mesh network.

Consistency Distillation with Target Timestep Selection and Decoupled Guidance

An addon module for portapack to add extra features to it for more fun.

对llama3进行全参微调、lora微调以及qlora微调。

Use PEFT or Full-parameter to finetune 400+ LLMs (Qwen2.5, Llama3.2, GLM4, Internlm2.5, Yi1.5, Mistral, Baichuan2, DeepSeek, ...) or 100+ MLLMs (Qwen2-VL, Qwen2-Audio, Llama3.2-Vision, Llava, InternVL...

A simple mesh network communications app powered by the Reticulum Network Stack.

《开源大模型食用指南》针对中国宝宝量身打造的基于Linux环境快速微调（全参数/Lora）、部署国内外开源大模型（LLM）/多模态大模型（MLLM）教程

tinySSB is "Secure Scuttlebutt over LoRa and BLE"

📚 Text Classification with LoRA (Low-Rank Adaptation) of Language Models - Efficiently fine-tune large language models for text classification tasks using the Stanford Sentiment Treebank (SST-2) data...

LoRa trainer for SDXL and SD15

A map of all Meshtastic nodes heard via MQTT.

A suite of tools for easy image tagging. Focused on LoRA training dataset creation and preparation

JORA: JAX Tensor-Parallel LoRA Library (ACL 2024)

[ICML2024 (Oral)] Official PyTorch implementation of DoRA: Weight-Decomposed Low-Rank Adaptation

SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models

Open Source Application for Advanced LLM Engineering: interact, train, fine-tune, and evaluate large language models on your own computer.

A library for easily merging multiple LLM experts, and efficiently train the merged LLM.

Phi-3.5 for Mac: Locally-run Vision and Language Models for Apple Silicon

SiLLM simplifies the process of training and running Large Language Models (LLMs) on Apple Silicon by leveraging the MLX framework.

X-LoRA: Mixture of LoRA Experts

Codebase for "CtrLoRA: An Extensible and Efficient Framework for Controllable Image Generation"

对llama3进行全参微调、lora微调以及qlora微调。

A simple mesh network communications app powered by the Reticulum Network Stack.

Official implementation of "DoRA: Weight-Decomposed Low-Rank Adaptation"

End to End Generative AI Industry Projects on LLM Models with Deployment_Awesome LLM Projects

A generalized framework for subspace tuning methods in parameter efficient fine-tuning.

大模型/LLM推理和部署理论与实践

A map of all Meshtastic nodes heard via MQTT.

An addon module for portapack to add extra features to it for more fun.

🚀 Easy, open-source LLM finetuning with one-line commands, seamless cloud integration, and popular optimization frameworks. ✨

This is the official repository for the paper "Flora: Low-Rank Adapters Are Secretly Gradient Compressors" in ICML 2024.

Official PyTorch Implementation for the "Recovering the Pre-Fine-Tuning Weights of Generative Models" paper (ICML 2024).

Finetune mistral-7b-instruct for sentence embeddings

Unified Efficient Fine-Tuning of 100+ LLMs (ACL 2024)

Finetune Llama 3.3, Mistral, Phi, Qwen 2.5 & Gemma LLMs 2-5x faster with 70% less memory

🧑‍🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), ga...

《开源大模型食用指南》针对中国宝宝量身打造的基于Linux环境快速微调（全参数/Lora）、部署国内外开源大模型（LLM）/多模态大模型（MLLM）教程

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

Use PEFT or Full-parameter to finetune 400+ LLMs (Qwen2.5, Llama3.2, GLM4, Internlm2.5, Yi1.5, Mistral, Baichuan2, DeepSeek, ...) or 100+ MLLMs (Qwen2-VL, Qwen2-Audio, Llama3.2-Vision, Llava, InternVL...

AirLLM 70B inference with single 4GB GPU

Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"

中文LLaMA&Alpaca大语言模型+本地CPU/GPU训练部署 (Chinese LLaMA & Alpaca LLMs)

Firefly: 大模型训练工具，支持训练Qwen2.5、Qwen2、Yi1.5、Phi-3、Llama3、Gemma、MiniCPM、Yi、Deepseek、Orion、Xverse、Mixtral-8x7B、Zephyr、Mistral、Baichuan2、Llma2、Llama、Qwen、Baichuan、ChatGLM2、InternLM、Ziya2、Vicuna、Bloom等大模型

Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs

LLM Finetuning with peft

SD-Trainer. LoRA & Dreambooth training scripts & GUI use kohya-ss's trainer, for diffusion model.

Meshtastic device firmware

OneTrainer is a one-stop solution for all your stable diffusion training needs.

stable diffusion webui colab

OneDiff: An out-of-the-box acceleration library for diffusion models.

Large-scale LLM inference engine

Using Low-rank adaptation to quickly fine-tune diffusion models.

ESP32/ESP8285-based High-Performance Radio Link for RC applications

《开源大模型食用指南》针对中国宝宝量身打造的基于Linux环境快速微调（全参数/Lora）、部署国内外开源大模型（LLM）/多模态大模型（MLLM）教程

A library for easily merging multiple LLM experts, and efficiently train the merged LLM.

A generalized framework for subspace tuning methods in parameter efficient fine-tuning.

Phi-3.5 for Mac: Locally-run Vision and Language Models for Apple Silicon

The official codes for "Aurora: Activating chinese chat capability for Mixtral-8x7B sparse Mixture-of-Experts through Instruction-Tuning"

Give your computer an AI Brain

Use PEFT or Full-parameter to finetune 400+ LLMs (Qwen2.5, Llama3.2, GLM4, Internlm2.5, Yi1.5, Mistral, Baichuan2, DeepSeek, ...) or 100+ MLLMs (Qwen2-VL, Qwen2-Audio, Llama3.2-Vision, Llava, InternVL...

SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models

Easy and Fast LLM finetuning on GPU or CPU.

SiLLM simplifies the process of training and running Large Language Models (LLMs) on Apple Silicon by leveraging the MLX framework.

Scripts of LLM pre-training and fine-tuning (w/wo LoRA, DeepSpeed)

Finetune Llama 3.3, Mistral, Phi, Qwen 2.5 & Gemma LLMs 2-5x faster with 70% less memory

Heltec Wireless Tracker (MakerFocus) ESP32/Oled/GNSS/Lora SKU: ZC-193-915

Large-scale LLM inference engine

📚 Text Classification with LoRA (Low-Rank Adaptation) of Language Models - Efficiently fine-tune large language models for text classification tasks using the Stanford Sentiment Treebank (SST-2) data...

A microframework on top of PyTorch with first-class citizen APIs for foundation model adaptation

Code for NOLA, an implementation of "nola: Compressing LoRA using Linear Combination of Random Basis"

该仓库主要记录 LLMs 算法工程师相关的顶会论文研读笔记（多模态、PEFT、小样本QA问答、RAG、LMMs可解释性、Agents、CoT）

[3DV 2025] iFusion: Inverting Diffusion for Pose-Free Reconstruction from Sparse Views

✏️0成本LLM微调上手项目，⚡️一步一步使用colab训练法律LLM，基于microsoft/phi-1_5、chatglm3，包含lora微调，全参微调