Gryphe / BlockMerge_GradientLinks
Merge Transformers language models by use of gradient parameters.
☆209Updated last year
Alternatives and similar repositories for BlockMerge_Gradient
Users that are interested in BlockMerge_Gradient are comparing it to the libraries listed below
Sorting:
- This is our own implementation of 'Layer Selective Rank Reduction'☆240Updated last year
- Low-Rank adapter extraction for fine-tuned transformers models☆180Updated last year
- A bagel, with everything.☆325Updated last year
- QLoRA: Efficient Finetuning of Quantized LLMs☆79Updated last year
- Load multiple LoRA modules simultaneously and automatically switch the appropriate combination of LoRA modules to generate the best answe…☆157Updated last year
- An unsupervised model merging algorithm for Transformers-based language models.☆108Updated last year
- Landmark Attention: Random-Access Infinite Context Length for Transformers QLoRA☆124Updated 2 years ago
- ☆74Updated 2 years ago
- Convenient wrapper for fine-tuning and inference of Large Language Models (LLMs) with several quantization techniques (GTPQ, bitsandbytes…☆146Updated 2 years ago
- ☆164Updated 4 months ago
- Model REVOLVER, a human in the loop model mixing system.☆33Updated 2 years ago
- Some simple scripts that I use day-to-day when working with LLMs and Huggingface Hub☆161Updated 2 years ago
- Landmark Attention: Random-Access Infinite Context Length for Transformers☆427Updated 2 years ago
- an implementation of Self-Extend, to expand the context window via grouped attention☆119Updated last year
- Spherical Merge Pytorch/HF format Language Models with minimal feature loss.☆141Updated 2 years ago
- Inference code for Mistral and Mixtral hacked up into original Llama implementation☆371Updated 2 years ago
- ☆95Updated 2 years ago
- Multipack distributed sampler for fast padding-free training of LLMs☆202Updated last year
- ☆416Updated 2 years ago
- Generate Synthetic Data Using OpenAI, MistralAI or AnthropicAI☆222Updated last year
- Notus is a collection of fine-tuned LLMs using SFT, DPO, SFT+DPO, and/or any other RLHF techniques, while always keeping a data-first app…☆170Updated last year
- batched loras☆347Updated 2 years ago
- Automated Identification of Redundant Layer Blocks for Pruning in Large Language Models☆258Updated last year
- ☆78Updated last year
- Code for the paper "SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot" with LLaMA implementation.☆71Updated 2 years ago
- GPTQLoRA: Efficient Finetuning of Quantized LLMs with GPTQ☆101Updated 2 years ago
- 1.58-bit LLaMa model☆83Updated last year
- GPT-2 small trained on phi-like data☆67Updated last year
- Experiments on speculative sampling with Llama models☆127Updated 2 years ago
- inference code for mixtral-8x7b-32kseqlen☆104Updated 2 years ago