AlpinDale / LLM-Shearing
Preprint: Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning
☆28Updated 9 months ago
Related projects ⓘ
Alternatives and complementary repositories for LLM-Shearing
- an implementation of Self-Extend, to expand the context window via grouped attention☆118Updated 10 months ago
- ☆27Updated last year
- look how they massacred my boy☆58Updated last month
- ☆49Updated 8 months ago
- Landmark Attention: Random-Access Infinite Context Length for Transformers QLoRA☆124Updated last year
- Fast approximate inference on a single GPU with sparsity aware offloading☆38Updated 10 months ago
- Automated prompting and scoring framework to evaluate LLMs using updated human knowledge prompts☆111Updated last year
- Full finetuning of large language models without large memory requirements☆93Updated 10 months ago
- Steer LLM outputs towards a certain topic/subject and enhance response capabilities using activation engineering by adding steering vecto…☆42Updated 8 months ago
- Model REVOLVER, a human in the loop model mixing system.☆33Updated last year
- An unsupervised model merging algorithm for Transformers-based language models.☆100Updated 6 months ago
- An easy-to-understand framework for LLM samplers that rewind and revise generated tokens☆113Updated 3 weeks ago
- GPT-2 small trained on phi-like data☆65Updated 9 months ago
- Comprehensive analysis of difference in performance of QLora, Lora, and Full Finetunes.☆81Updated last year
- Low-Rank adapter extraction for fine-tuned transformers model☆162Updated 6 months ago
- MiniHF is an inference, human preference data collection, and fine-tuning tool for local language models. It is intended to help the user…☆152Updated this week
- ☆72Updated last year
- ☆149Updated 4 months ago
- inference code for mixtral-8x7b-32kseqlen☆98Updated 11 months ago
- RWKV-7: Surpassing GPT☆45Updated this week
- ☆64Updated 5 months ago
- Demonstration that finetuning RoPE model on larger sequences than the pre-trained model adapts the model context limit☆63Updated last year
- Code for the paper "SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot" with LLaMA implementation.☆70Updated last year
- Merge Transformers language models by use of gradient parameters.☆201Updated 3 months ago
- Steer LLM outputs towards a certain topic/subject and enhance response capabilities using activation engineering by adding steering vecto…☆203Updated 6 months ago
- This is our own implementation of 'Layer Selective Rank Reduction'☆232Updated 5 months ago
- Let's create synthetic textbooks together :)☆70Updated 9 months ago
- QLoRA: Efficient Finetuning of Quantized LLMs☆77Updated 7 months ago
- ☆21Updated 5 months ago
- entropix style sampling + GUI☆25Updated 3 weeks ago