leehanchung / lora-instructLinks
Finetune Falcon, LLaMA, MPT, and RedPajama on consumer hardware using PEFT LoRA
☆103Updated 2 weeks ago
Alternatives and similar repositories for lora-instruct
Users that are interested in lora-instruct are comparing it to the libraries listed below
Sorting:
- QLoRA: Efficient Finetuning of Quantized LLMs☆78Updated last year
- Exploring finetuning public checkpoints on filter 8K sequences on Pile☆114Updated 2 years ago
- Spherical Merge Pytorch/HF format Language Models with minimal feature loss.☆123Updated last year
- Tune MPTs☆84Updated last year
- Small and Efficient Mathematical Reasoning LLMs☆71Updated last year
- Experiments with generating opensource language model assistants☆97Updated 2 years ago
- QLoRA with Enhanced Multi GPU Support☆37Updated last year
- ☆37Updated 2 years ago
- Multi-Domain Expert Learning☆66Updated last year
- Comprehensive analysis of difference in performance of QLora, Lora, and Full Finetunes.☆81Updated last year
- Sakura-SOLAR-DPO: Merge, SFT, and DPO☆116Updated last year
- Instruct-tune Open LLaMA / RedPajama / StableLM models on consumer hardware using QLoRA☆81Updated last year
- GPTQLoRA: Efficient Finetuning of Quantized LLMs with GPTQ☆103Updated 2 years ago
- Code repository for the c-BTM paper☆106Updated last year
- ☆87Updated last year
- Notus is a collection of fine-tuned LLMs using SFT, DPO, SFT+DPO, and/or any other RLHF techniques, while always keeping a data-first app…☆167Updated last year
- Reimplementation of the task generation part from the Alpaca paper☆118Updated 2 years ago
- The Next Generation Multi-Modality Superintelligence☆70Updated 9 months ago
- Patch for MPT-7B which allows using and training a LoRA☆58Updated 2 years ago
- ☆95Updated last year
- Demonstration that finetuning RoPE model on larger sequences than the pre-trained model adapts the model context limit☆62Updated last year
- Fully fine-tune large models like Mistral, Llama-2-13B, or Qwen-14B completely for free☆230Updated 7 months ago
- Evaluating LLMs with CommonGen-Lite☆90Updated last year
- Multipack distributed sampler for fast padding-free training of LLMs☆188Updated 9 months ago
- ☆23Updated last year
- ☆92Updated last year
- The GeoV model is a large langauge model designed by Georges Harik and uses Rotary Positional Embeddings with Relative distances (RoPER).…☆121Updated 2 years ago
- inference code for mixtral-8x7b-32kseqlen☆99Updated last year
- Simple replication of [ColBERT-v1](https://arxiv.org/abs/2004.12832).☆80Updated last year
- ☆76Updated last year