Alternatives and similar repositories for lora-merge

Users that are interested in lora-merge are comparing it to the libraries listed below

• nyunAI / PruneGPT
  ☆51Updated last year
• zarakiquemparte / zaraki-tools
  ☆27Updated 2 years ago
• kyegomez / Finetuning-Suite
  Finetune any model on HF in less than 30 seconds
  ☆57Updated 2 weeks ago
• Cerebras / DocChat
  GPT-4 Level Conversational QA Trained In a Few Hours
  ☆64Updated last year
• ElleLeonne / Lightning-ReLoRA
  A public implementation of the ReLoRA pretraining method, built on Lightning-AI's Pytorch Lightning suite.
  ☆34Updated last year
• the-crypt-keeper / the-muse
  Experimental sampler to make LLMs more creative
  ☆31Updated 2 years ago
• huseinzol05 / transformers-continuous-batching
  Lightweight continuous batching OpenAI compatibility using HuggingFace Transformers include T5 and Whisper.
  ☆27Updated 6 months ago
• deep-diver / gradio-chat
  HuggingChat like UI in Gradio
  ☆71Updated 2 years ago
• LLM360 / crystalcoder-data-prep
  Data preparation code for CrystalCoder 7B LLM
  ☆45Updated last year
• EduardTalianu / EntropixLab
  entropix style sampling + GUI
  ☆27Updated 10 months ago
• arcee-ai / DAM
  ☆54Updated 10 months ago
• thooton / muse
  Let's create synthetic textbooks together :)
  ☆75Updated last year
• serp-ai / Parameter-Efficient-MoE
  Parameter-Efficient Sparsity Crafting From Dense to Mixture-of-Experts for Instruction Tuning on General Tasks
  ☆31Updated last year
• monk1337 / auto-ollama
  run ollama & gguf easily with a single command
  ☆52Updated last year
• silphendio / sliced_llama
  Simple LLM inference server
  ☆20Updated last year
• Gryphe / MergeMonster
  An unsupervised model merging algorithm for Transformers-based language models.
  ☆107Updated last year
• LLM360 / k2-data-prep
  ☆21Updated last year
• xaedes / llama.cpp
  Port of Facebook's LLaMA model in C/C++
  ☆22Updated last year
• Digitous / ModelREVOLVER
  Model REVOLVER, a human in the loop model mixing system.
  ☆33Updated 2 years ago
• alexrs / herd
  Mixture of Expert (MoE) techniques for enhancing LLM performance through expert-driven prompt mapping and adapter combinations.
  ☆12Updated last year
• Zyphra / Zyda_processing
  ☆39Updated last year
• emrgnt-cmplxty / zero-shot-replication
  ☆74Updated 2 years ago
• austinsilveria / tricksy
  Fast approximate inference on a single GPU with sparsity aware offloading
  ☆38Updated last year
• geronimi73 / 3090_shorts
  minimal scripts for 24GB VRAM GPUs. training, inference, whatever
  ☆42Updated this week
• shivamsanju / ragswift
  🚀 Scale your RAG pipeline using Ragswift: A scalable centralized embeddings management platform
  ☆38Updated last year
• attashe / ModifiedBeamSampler
  Modified Beam Search with periodical restart
  ☆12Updated last year
• VatsaDev / NanoPhi-alpha
  GPT-2 small trained on phi-like data
  ☆67Updated last year
• The-Swarm-Corporation / AgentParse
  AgentParse is a high-performance parsing library designed to map various structured data formats (such as Pydantic models, JSON, YAML, an…
  ☆16Updated this week
• SebastianBodza / EnsembleForecasting
  Using multiple LLMs for ensemble Forecasting
  ☆16Updated last year
• taprosoft / llm_finetuning
  Convenient wrapper for fine-tuning and inference of Large Language Models (LLMs) with several quantization techniques (GTPQ, bitsandbytes…
  ☆146Updated last year