vihangd / alpaca-qlora
Instruct-tune Open LLaMA / RedPajama / StableLM models on consumer hardware using QLoRA
☆81Updated last year
Alternatives and similar repositories for alpaca-qlora:
Users that are interested in alpaca-qlora are comparing it to the libraries listed below
- Spherical Merge Pytorch/HF format Language Models with minimal feature loss.☆121Updated last year
- GPTQLoRA: Efficient Finetuning of Quantized LLMs with GPTQ☆103Updated last year
- Unofficial implementation of AlpaGasus☆91Updated last year
- Load multiple LoRA modules simultaneously and automatically switch the appropriate combination of LoRA modules to generate the best answe…☆150Updated last year
- A Multilingual Replicable Instruction-Following Model☆93Updated last year
- Official implementation for 'Extending LLMs’ Context Window with 100 Samples'☆77Updated last year
- QLoRA: Efficient Finetuning of Quantized LLMs☆78Updated last year
- Positional Skip-wise Training for Efficient Context Window Extension of LLMs to Extremely Length (ICLR 2024)☆205Updated 11 months ago
- Small and Efficient Mathematical Reasoning LLMs☆71Updated last year
- ☆75Updated last year
- Open Source WizardCoder Dataset☆158Updated last year
- Reverse Instructions to generate instruction tuning data with corpus examples☆209Updated last year
- ☆94Updated last year
- MultilingualSIFT: Multilingual Supervised Instruction Fine-tuning☆90Updated last year
- Due to restriction of LLaMA, we try to reimplement BLOOM-LoRA (much less restricted BLOOM license here https://huggingface.co/spaces/bigs…☆184Updated last year
- Scripts for fine-tuning Llama2 via SFT and DPO.☆197Updated last year
- Finetune Falcon, LLaMA, MPT, and RedPajama on consumer hardware using PEFT LoRA☆103Updated 9 months ago
- Exploring finetuning public checkpoints on filter 8K sequences on Pile☆115Updated 2 years ago
- Inference script for Meta's LLaMA models using Hugging Face wrapper☆110Updated 2 years ago
- [EMNLP 2023] The CoT Collection: Improving Zero-shot and Few-shot Learning of Language Models via Chain-of-Thought Fine-Tuning☆240Updated last year
- ModuleFormer is a MoE-based architecture that includes two different types of experts: stick-breaking attention heads and feedforward exp…☆220Updated last year
- evol augment any dataset online☆59Updated last year
- ☆97Updated last year
- A bagel, with everything.☆320Updated last year
- [ICLR 2023] Codebase for Copy-Generator model, including an implementation of kNN-LM☆186Updated 3 months ago
- [AAAI 2024] Investigating the Effectiveness of Task-Agnostic Prefix Prompt for Instruction Following☆79Updated 7 months ago
- Parameter-Efficient Sparsity Crafting From Dense to Mixture-of-Experts for Instruction Tuning on General Tasks☆143Updated 7 months ago
- Wrapper to easily generate the chat template for Llama2☆64Updated last year
- Patch for MPT-7B which allows using and training a LoRA☆58Updated last year
- Lightweight demos for finetuning LLMs. Powered by 🤗 transformers and open-source datasets.☆76Updated 6 months ago