rmihaylov / mpttune
Tune MPTs
☆84Updated last year
Alternatives and similar repositories for mpttune:
Users that are interested in mpttune are comparing it to the libraries listed below
- QLoRA: Efficient Finetuning of Quantized LLMs☆77Updated 11 months ago
- Full finetuning of large language models without large memory requirements☆93Updated last year
- GPTQLoRA: Efficient Finetuning of Quantized LLMs with GPTQ☆99Updated last year
- Finetune Falcon, LLaMA, MPT, and RedPajama on consumer hardware using PEFT LoRA☆102Updated 7 months ago
- ☆49Updated 11 months ago
- experiments with inference on llama☆104Updated 9 months ago
- Exploring finetuning public checkpoints on filter 8K sequences on Pile☆115Updated last year
- Multi-Domain Expert Learning☆67Updated last year
- Comprehensive analysis of difference in performance of QLora, Lora, and Full Finetunes.☆82Updated last year
- QLoRA with Enhanced Multi GPU Support☆36Updated last year
- Spherical Merge Pytorch/HF format Language Models with minimal feature loss.☆117Updated last year
- This is our own implementation of 'Layer Selective Rank Reduction'☆233Updated 9 months ago
- Experiments with generating opensource language model assistants☆97Updated last year
- Patch for MPT-7B which allows using and training a LoRA☆58Updated last year
- Low-Rank adapter extraction for fine-tuned transformers models☆171Updated 10 months ago
- an implementation of Self-Extend, to expand the context window via grouped attention☆118Updated last year
- Convenient wrapper for fine-tuning and inference of Large Language Models (LLMs) with several quantization techniques (GTPQ, bitsandbytes…☆147Updated last year
- Code repository for the c-BTM paper☆105Updated last year
- Fully fine-tune large models like Mistral, Llama-2-13B, or Qwen-14B completely for free☆230Updated 4 months ago
- ☆94Updated last year
- Demonstration that finetuning RoPE model on larger sequences than the pre-trained model adapts the model context limit☆63Updated last year
- Command-line script for inferencing from models such as MPT-7B-Chat☆101Updated last year
- ☆92Updated last year
- inference code for mixtral-8x7b-32kseqlen☆99Updated last year
- Zeus LLM Trainer is a rewrite of Stanford Alpaca aiming to be the trainer for all Large Language Models☆69Updated last year
- An efficent implementation of the method proposed in "The Era of 1-bit LLMs"☆154Updated 4 months ago
- 4 bits quantization of SantaCoder using GPTQ☆51Updated last year
- ☆113Updated 5 months ago
- ☆73Updated last year
- Multipack distributed sampler for fast padding-free training of LLMs☆186Updated 7 months ago