Gryphe / BlockMerge_Gradient
Merge Transformers language models by use of gradient parameters.
☆205Updated 7 months ago
Alternatives and similar repositories for BlockMerge_Gradient:
Users that are interested in BlockMerge_Gradient are comparing it to the libraries listed below
- This is our own implementation of 'Layer Selective Rank Reduction'☆233Updated 10 months ago
- QLoRA: Efficient Finetuning of Quantized LLMs☆77Updated 11 months ago
- Low-Rank adapter extraction for fine-tuned transformers models☆171Updated 11 months ago
- Spherical Merge Pytorch/HF format Language Models with minimal feature loss.☆119Updated last year
- A bagel, with everything.☆317Updated 11 months ago
- ☆94Updated last year
- An unsupervised model merging algorithm for Transformers-based language models.☆104Updated 11 months ago
- Landmark Attention: Random-Access Infinite Context Length for Transformers☆421Updated last year
- Automated Identification of Redundant Layer Blocks for Pruning in Large Language Models☆227Updated 11 months ago
- Landmark Attention: Random-Access Infinite Context Length for Transformers QLoRA☆123Updated last year
- Model REVOLVER, a human in the loop model mixing system.☆33Updated last year
- ☆152Updated 8 months ago
- A pipeline for LLM knowledge distillation☆99Updated this week
- Load multiple LoRA modules simultaneously and automatically switch the appropriate combination of LoRA modules to generate the best answe…☆150Updated last year
- Some simple scripts that I use day-to-day when working with LLMs and Huggingface Hub☆159Updated last year
- ☆73Updated last year
- an implementation of Self-Extend, to expand the context window via grouped attention☆118Updated last year
- Multipack distributed sampler for fast padding-free training of LLMs☆186Updated 7 months ago
- GPTQLoRA: Efficient Finetuning of Quantized LLMs with GPTQ☆100Updated last year
- Convenient wrapper for fine-tuning and inference of Large Language Models (LLMs) with several quantization techniques (GTPQ, bitsandbytes…☆147Updated last year
- Comprehensive analysis of difference in performance of QLora, Lora, and Full Finetunes.☆82Updated last year
- Positional Skip-wise Training for Efficient Context Window Extension of LLMs to Extremely Length (ICLR 2024)☆205Updated 10 months ago
- EvolKit is an innovative framework designed to automatically enhance the complexity of instructions used for fine-tuning Large Language M…☆208Updated 5 months ago
- An easy-to-understand framework for LLM samplers that rewind and revise generated tokens☆138Updated last month
- GPT-2 small trained on phi-like data☆65Updated last year
- Fast & more realistic evaluation of chat language models. Includes leaderboard.☆185Updated last year
- batched loras☆340Updated last year
- Parameter-Efficient Sparsity Crafting From Dense to Mixture-of-Experts for Instruction Tuning on General Tasks☆141Updated 6 months ago
- Experiments on speculative sampling with Llama models☆125Updated last year
- Pre-training code for Amber 7B LLM☆165Updated 10 months ago