AlpinDale / LLM-ShearingLinks
Preprint: Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning
☆28Updated last year
Alternatives and similar repositories for LLM-Shearing
Users that are interested in LLM-Shearing are comparing it to the libraries listed below
Sorting:
- MiniHF is an inference, human preference data collection, and fine-tuning tool for local language models. It is intended to help the user…☆183Updated 2 months ago
- This is our own implementation of 'Layer Selective Rank Reduction'☆240Updated last year
- inference code for mixtral-8x7b-32kseqlen☆104Updated 2 years ago
- An easy-to-understand framework for LLM samplers that rewind and revise generated tokens☆150Updated this week
- Full finetuning of large language models without large memory requirements☆94Updated 3 months ago
- Code for the paper "SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot" with LLaMA implementation.☆71Updated 2 years ago
- Steer LLM outputs towards a certain topic/subject and enhance response capabilities using activation engineering by adding steering vecto…☆43Updated last year
- ☆137Updated last year
- Command-line script for inferencing from models such as falcon-7b-instruct☆75Updated 2 years ago
- ☆74Updated 2 years ago
- ☆27Updated 2 years ago
- ☆165Updated 5 months ago
- Landmark Attention: Random-Access Infinite Context Length for Transformers QLoRA☆124Updated 2 years ago
- Simplex Random Feature attention, in PyTorch☆75Updated 2 years ago
- ☆23Updated last year
- Implementation of mamba with rust☆89Updated last year
- Merge Transformers language models by use of gradient parameters.☆211Updated last year
- Low-Rank adapter extraction for fine-tuned transformers models☆180Updated last year
- Let's create synthetic textbooks together :)☆75Updated last year
- ☆50Updated last year
- ☆68Updated last year
- GPT-2 small trained on phi-like data☆67Updated last year
- An unsupervised model merging algorithm for Transformers-based language models.☆108Updated last year
- an implementation of Self-Extend, to expand the context window via grouped attention☆119Updated 2 years ago
- Demonstration that finetuning RoPE model on larger sequences than the pre-trained model adapts the model context limit☆63Updated 2 years ago
- Experimental LLM Inference UX to aid in creative writing☆127Updated last year
- A Collection of Pydantic Models to Abstract IRL☆36Updated last month
- ☆62Updated 2 years ago
- The GeoV model is a large langauge model designed by Georges Harik and uses Rotary Positional Embeddings with Relative distances (RoPER).…☆121Updated 2 years ago
- A more memory-efficient rewrite of the HF transformers implementation of Llama for use with quantized weights.☆64Updated 2 years ago