AlpinDale / sparsegpt-for-LLaMALinks
Code for the paper "SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot" with LLaMA implementation.
☆70Updated 2 years ago
Alternatives and similar repositories for sparsegpt-for-LLaMA
Users that are interested in sparsegpt-for-LLaMA are comparing it to the libraries listed below
Sorting:
- Landmark Attention: Random-Access Infinite Context Length for Transformers QLoRA☆122Updated last year
- Model REVOLVER, a human in the loop model mixing system.☆32Updated last year
- An unsupervised model merging algorithm for Transformers-based language models.☆104Updated last year
- GPT-2 small trained on phi-like data☆66Updated last year
- GPTQLoRA: Efficient Finetuning of Quantized LLMs with GPTQ☆102Updated 2 years ago
- Efficient 3bit/4bit quantization of LLaMA models☆19Updated 2 years ago
- Automated prompting and scoring framework to evaluate LLMs using updated human knowledge prompts☆109Updated last year
- Full finetuning of large language models without large memory requirements☆93Updated last year
- ☆72Updated last year
- QLoRA: Efficient Finetuning of Quantized LLMs☆77Updated last year
- inference code for mixtral-8x7b-32kseqlen☆99Updated last year
- Comprehensive analysis of difference in performance of QLora, Lora, and Full Finetunes.☆81Updated last year
- Code for paper: "QuIP: 2-Bit Quantization of Large Language Models With Guarantees" adapted for Llama models☆35Updated last year
- ☆40Updated 2 years ago
- Low-Rank adapter extraction for fine-tuned transformers models☆171Updated last year
- ☆26Updated last year
- an implementation of Self-Extend, to expand the context window via grouped attention☆119Updated last year
- This is our own implementation of 'Layer Selective Rank Reduction'☆238Updated last year
- SparseGPT + GPTQ Compression of LLMs like LLaMa, OPT, Pythia☆40Updated 2 years ago
- Merge Transformers language models by use of gradient parameters.☆206Updated 9 months ago
- Conversion script adapting vicuna dataset into alpaca format for use with oobabooga's trainer☆12Updated last year
- QuIP quantization☆51Updated last year
- Zeus LLM Trainer is a rewrite of Stanford Alpaca aiming to be the trainer for all Large Language Models☆68Updated last year
- Code for the paper "QMoE: Practical Sub-1-Bit Compression of Trillion-Parameter Models".☆275Updated last year
- Demonstration that finetuning RoPE model on larger sequences than the pre-trained model adapts the model context limit☆62Updated last year
- Code repository for the c-BTM paper☆106Updated last year
- Command-line script for inferencing from models such as MPT-7B-Chat☆100Updated last year
- Image Diffusion block merging technique applied to transformers based Language Models.☆53Updated 2 years ago
- Preprint: Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning☆28Updated last year
- Let's create synthetic textbooks together :)☆75Updated last year