leehanchung / lora-instruct
Finetune Falcon, LLaMA, MPT, and RedPajama on consumer hardware using PEFT LoRA
☆102Updated 7 months ago
Alternatives and similar repositories for lora-instruct:
Users that are interested in lora-instruct are comparing it to the libraries listed below
- QLoRA: Efficient Finetuning of Quantized LLMs☆77Updated 11 months ago
- 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…☆165Updated last year
- Small and Efficient Mathematical Reasoning LLMs☆71Updated last year
- ☆87Updated last year
- Reimplementation of the task generation part from the Alpaca paper☆119Updated last year
- Comprehensive analysis of difference in performance of QLora, Lora, and Full Finetunes.☆82Updated last year
- Code repository for the c-BTM paper☆106Updated last year
- Tune MPTs☆84Updated last year
- Official code for ACL 2023 (short, findings) paper "Recursion of Thought: A Divide and Conquer Approach to Multi-Context Reasoning with L…☆43Updated last year
- Evaluating LLMs with CommonGen-Lite☆89Updated 11 months ago
- Simple replication of [ColBERT-v1](https://arxiv.org/abs/2004.12832).☆80Updated 11 months ago
- Sakura-SOLAR-DPO: Merge, SFT, and DPO☆116Updated last year
- Spherical Merge Pytorch/HF format Language Models with minimal feature loss.☆117Updated last year
- QLoRA with Enhanced Multi GPU Support☆36Updated last year
- manage histories of LLM applied applications☆88Updated last year
- ☆92Updated last year
- Full finetuning of large language models without large memory requirements☆93Updated last year
- Mixing Language Models with Self-Verification and Meta-Verification☆102Updated 3 months ago
- ☆40Updated 10 months ago
- Experiments with generating opensource language model assistants☆97Updated last year
- Zeus LLM Trainer is a rewrite of Stanford Alpaca aiming to be the trainer for all Large Language Models☆69Updated last year
- Exploring finetuning public checkpoints on filter 8K sequences on Pile☆115Updated last year
- ☆48Updated last year
- ☆24Updated last year
- Multi-Domain Expert Learning☆67Updated last year
- inference code for mixtral-8x7b-32kseqlen☆99Updated last year
- Patch for MPT-7B which allows using and training a LoRA☆58Updated last year
- ☆94Updated last year
- The GeoV model is a large langauge model designed by Georges Harik and uses Rotary Positional Embeddings with Relative distances (RoPER).…☆121Updated last year
- GPTQLoRA: Efficient Finetuning of Quantized LLMs with GPTQ☆99Updated last year