VITA-Group / Q-GaLore
Q-GaLore: Quantized GaLore with INT4 Projection and Layer-Adaptive Low-Rank Gradients.
☆196Updated 7 months ago
Alternatives and similar repositories for Q-GaLore:
Users that are interested in Q-GaLore are comparing it to the libraries listed below
- Automated Identification of Redundant Layer Blocks for Pruning in Large Language Models☆223Updated 10 months ago
- An efficent implementation of the method proposed in "The Era of 1-bit LLMs"☆154Updated 4 months ago
- PyTorch implementation of models from the Zamba2 series.☆177Updated last month
- Repo for "LoLCATs: On Low-Rank Linearizing of Large Language Models"☆222Updated last month
- EfficientQAT: Efficient Quantization-Aware Training for Large Language Models☆250Updated 5 months ago
- ☆113Updated 5 months ago
- ☆193Updated 3 months ago
- Memory layers use a trainable key-value lookup mechanism to add extra parameters to a model without increasing FLOPs. Conceptually, spars…☆305Updated 3 months ago
- Code for the paper "QMoE: Practical Sub-1-Bit Compression of Trillion-Parameter Models".☆270Updated last year
- Manage scalable open LLM inference endpoints in Slurm clusters☆253Updated 8 months ago
- PB-LLM: Partially Binarized Large Language Models☆151Updated last year
- Code for "LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding", ACL 2024☆277Updated 2 weeks ago
- LongRoPE is a novel method that can extends the context window of pre-trained LLMs to an impressive 2048k tokens.☆201Updated 6 months ago
- Official PyTorch implementation of QA-LoRA☆127Updated last year
- Load multiple LoRA modules simultaneously and automatically switch the appropriate combination of LoRA modules to generate the best answe…☆150Updated last year
- Prune transformer layers☆68Updated 9 months ago
- ☆126Updated 6 months ago
- Parameter-Efficient Sparsity Crafting From Dense to Mixture-of-Experts for Instruction Tuning on General Tasks☆140Updated 5 months ago
- Implementation of DoRA☆290Updated 9 months ago
- A family of compressed models obtained via pruning and knowledge distillation☆329Updated 4 months ago
- Positional Skip-wise Training for Efficient Context Window Extension of LLMs to Extremely Length (ICLR 2024)☆204Updated 9 months ago
- OpenCoconut implements a latent reasoning paradigm where we generate thoughts before decoding.☆167Updated last month
- Multipack distributed sampler for fast padding-free training of LLMs☆186Updated 7 months ago
- ☆125Updated last year
- For releasing code related to compression methods for transformers, accompanying our publications☆413Updated last month
- A pipeline for LLM knowledge distillation☆96Updated last month
- EvolKit is an innovative framework designed to automatically enhance the complexity of instructions used for fine-tuning Large Language M…☆204Updated 4 months ago
- Low-Rank adapter extraction for fine-tuned transformers models☆171Updated 10 months ago
- Fast Matrix Multiplications for Lookup Table-Quantized LLMs☆231Updated 2 weeks ago
- The official repo for "LLoCo: Learning Long Contexts Offline"☆114Updated 8 months ago