BlinkDL / LM-Trick-QuestionsLinks
Here we collect trick questions and failed tasks for open source LLMs to improve them.
☆32Updated 2 years ago
Alternatives and similar repositories for LM-Trick-Questions
Users that are interested in LM-Trick-Questions are comparing it to the libraries listed below
Sorting:
- 32 times longer context window than vanilla Transformers and up to 4 times longer than memory efficient Transformers.☆49Updated 2 years ago
- Official repository for the paper "SwitchHead: Accelerating Transformers with Mixture-of-Experts Attention"☆99Updated last year
- Let us make Psychohistory (as in Asimov) a reality, and accessible to everyone. Useful for LLM grounding and games / fiction / business /…☆40Updated 2 years ago
- Structural Pruning for LLaMA☆54Updated 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
- Explorations into adversarial losses on top of autoregressive loss for language modeling☆38Updated 7 months ago
- Implementation of the Mamba SSM with hf_integration.☆56Updated last year
- Here we will test various linear attention designs.☆62Updated last year
- Griffin MQA + Hawk Linear RNN Hybrid☆89Updated last year
- ☆105Updated last year
- SparseGPT + GPTQ Compression of LLMs like LLaMa, OPT, Pythia☆41Updated 2 years ago
- Implementation of "LM-Infinite: Simple On-the-Fly Length Generalization for Large Language Models"☆39Updated 10 months ago
- DPO, but faster 🚀☆44Updated 10 months ago
- Utilities for Training Very Large Models☆58Updated last year
- The reproduct of the paper - Aligner: Achieving Efficient Alignment through Weak-to-Strong Correction☆22Updated last year
- Contextual Position Encoding but with some custom CUDA Kernels https://arxiv.org/abs/2405.18719☆22Updated last year
- Some personal experiments around routing tokens to different autoregressive attention, akin to mixture-of-experts☆122Updated 11 months ago
- ☆34Updated last year
- Official repository for the paper "Approximating Two-Layer Feedforward Networks for Efficient Transformers"☆38Updated 3 months ago
- Tools for content datamining and NLP at scale☆44Updated last year
- [ICML'24 Oral] The official code of "DiJiang: Efficient Large Language Models through Compact Kernelization", a novel DCT-based linear at…☆102Updated last year
- ☆32Updated last year
- BFloat16 Fused Adam Operator for PyTorch☆15Updated 10 months ago
- Script for processing OpenAI's PRM800K process supervision dataset into an Alpaca-style instruction-response format☆27Updated 2 years ago
- A repository for research on medium sized language models.☆78Updated last year
- RWKV model implementation☆38Updated 2 years ago
- ☆20Updated last year
- ☆39Updated last year
- GoldFinch and other hybrid transformer components☆45Updated last year
- Repository for CPU Kernel Generation for LLM Inference☆26Updated 2 years ago