kuleshov / minillm
MiniLLM is a minimal system for running modern LLMs on consumer-grade GPUs
☆905Updated last year
Alternatives and similar repositories for minillm:
Users that are interested in minillm are comparing it to the libraries listed below
- ☆1,465Updated last year
- Simple UI for LLM Model Finetuning☆2,063Updated last year
- Quantized inference code for LLaMA models☆1,052Updated 2 years ago
- Finetuning Large Language Models on One Consumer GPU in 2 Bits☆720Updated 10 months ago
- 4 bits quantization of LLaMA using GPTQ☆3,046Updated 8 months ago
- ☆535Updated last year
- Alpaca dataset from Stanford, cleaned and curated☆1,546Updated last year
- Large language models (LLMs) made easy, EasyLM is a one stop solution for pre-training, finetuning, evaluating and serving LLMs in JAX/Fl…☆2,464Updated 7 months ago
- LaMini-LM: A Diverse Herd of Distilled Models from Large-Scale Instructions☆820Updated last year
- Build, customize and control you own LLMs. From data pre-processing to fine-tuning, xTuring provides an easy way to personalize open-sour…☆2,641Updated 6 months ago
- Salesforce open-source LLMs with 8k sequence length.☆716Updated 2 months ago
- C++ implementation for BLOOM☆809Updated last year
- Fine-tune mistral-7B on 3090s, a100s, h100s☆709Updated last year
- Llama 2 Everywhere (L2E)☆1,516Updated 2 months ago
- Customizable implementation of the self-instruct paper.☆1,040Updated last year
- LLM as a Chatbot Service☆3,310Updated last year
- LLM that combines the principles of wizardLM and vicunaLM☆716Updated last year
- [NeurIPS 2023] MeZO: Fine-Tuning Language Models with Just Forward Passes. https://arxiv.org/abs/2305.17333☆1,099Updated last year
- ☆458Updated last year
- C++ implementation for 💫StarCoder☆453Updated last year
- An open-source implementation of Google's PaLM models☆818Updated 9 months ago
- Tune any FALCON in 4-bit☆466Updated last year
- Public repo for the NeurIPS 2023 paper "Unlimiformer: Long-Range Transformers with Unlimited Length Input"☆1,059Updated last year
- A more memory-efficient rewrite of the HF transformers implementation of Llama for use with quantized weights.☆2,846Updated last year
- A collection of modular datasets generated by GPT-4, General-Instruct - Roleplay-Instruct - Code-Instruct - and Toolformer☆1,628Updated last year
- Code for fine-tuning Platypus fam LLMs using LoRA☆628Updated last year
- The complete training code of the open-source high-performance Llama model, including the full process from pre-training to RLHF.☆44Updated last year
- A tiny library for coding with large language models.☆1,227Updated 8 months ago
- fastLLaMa: An experimental high-performance framework for running Decoder-only LLMs with 4-bit quantization in Python using a C/C++ backe…☆408Updated last year
- [NeurIPS 22] [AAAI 24] Recurrent Transformer-based long-context architecture.☆760Updated 5 months ago