Alternatives and similar repositories for qlora-inference-multi-gpu:

Users that are interested in qlora-inference-multi-gpu are comparing it to the libraries listed below

• official-elinas / zeus-llm-trainer
  Zeus LLM Trainer is a rewrite of Stanford Alpaca aiming to be the trainer for all Large Language Models
  ☆69Updated last year
• cloneofsimo / auto_llm_codebase_analysis
  ☆26Updated 11 months ago
• austinsilveria / tricksy
  Fast approximate inference on a single GPU with sparsity aware offloading
  ☆38Updated last year
• SebastianBodza / EnsembleForecasting
  Using multiple LLMs for ensemble Forecasting
  ☆16Updated last year
• zarakiquemparte / zaraki-tools
  ☆27Updated last year
• wangitu / Ada-Instruct
  ☆17Updated 10 months ago
• kyegomez / Finetuning-Suite
  Finetune any model on HF in less than 30 seconds
  ☆58Updated 3 weeks ago
• attashe / ModifiedBeamSampler
  Modified Beam Search with periodical restart
  ☆12Updated 5 months ago
• deepshard / mixtral-8x7b-Inference
  Eh, simple and works.
  ☆27Updated last year
• EdwardDali / EntropixLab
  entropix style sampling + GUI
  ☆25Updated 3 months ago
• kaiokendev / cutoff-len-is-context-len
  Demonstration that finetuning RoPE model on larger sequences than the pre-trained model adapts the model context limit
  ☆63Updated last year
• ElleLeonne / Lightning-ReLoRA
  A public implementation of the ReLoRA pretraining method, built on Lightning-AI's Pytorch Lightning suite.
  ☆33Updated 11 months ago
• BBuf / RWKV-World-HF-Tokenizer
  ☆34Updated 7 months ago
• mzbac / mlx-moe
  Scripts to create your own moe models using mlx
  ☆86Updated 11 months ago
• malaysia-ai / transformers-openai-api
  Lightweight continuous batching OpenAI compatibility using HuggingFace Transformers include T5 and Whisper.
  ☆20Updated this week
• camenduru / MiniGPT-v2-colab
  ☆29Updated last year
• kyegomez / FastFF
  Zeta implementation of a reusable and plug in and play feedforward from the paper "Exponentially Faster Language Modeling"
  ☆15Updated 3 months ago
• matthewrenze / jhu-concise-cot
  The Benefits of a Concise Chain of Thought on Problem Solving in Large Language Models
  ☆21Updated 2 months ago
• camenduru / nvidia-llm-colab
  ☆14Updated last year
• the-crypt-keeper / the-muse
  Experimental sampler to make LLMs more creative
  ☆30Updated last year
• deep-diver / LLM-Pref-Mark-UI
  ☆37Updated last year
• PicoCreator / RWKV-LM-LoRA
  RWKV is a RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best …
  ☆10Updated last year
• phunterlau / paper_without_code
  LLM reads a paper and produce a working prototype
  ☆48Updated 2 weeks ago
• NolanoOrg / llama-int4-quant
  ☆26Updated last year
• CogNLP / CogAGENT
  ☆36Updated last year
• nyunAI / PruneGPT
  ☆53Updated 8 months ago
• diicellman / dynamite-dogs
  BH hackathon
  ☆14Updated 10 months ago
• LLM360 / k2-data-prep
  ☆20Updated 8 months ago