view article Article Model2Vec: Distill a Small Fast Model from any Sentence Transformer By Pringled • 9 days ago • 48
RevisEval: Improving LLM-as-a-Judge via Response-Adapted References Paper • 2410.05193 • Published 15 days ago • 12
view article Article Automatic Hallucination detection with SelfCheckGPT NLI By dhuynh95 • Nov 27, 2023 • 4
Zeroshot Classifiers Collection These are my current best zeroshot classifiers. Some of my older models are downloaded more often, but the models in this collection are newer/better. • 11 items • Updated Apr 3 • 109
Mutual Reasoning Makes Smaller LLMs Stronger Problem-Solvers Paper • 2408.06195 • Published Aug 12 • 61
Gemma 2: Improving Open Language Models at a Practical Size Paper • 2408.00118 • Published Jul 31 • 73
Repurposing Language Models into Embedding Models: Finding the Compute-Optimal Recipe Paper • 2406.04165 • Published Jun 6 • 1
Improving Text Embeddings for Smaller Language Models Using Contrastive Fine-tuning Paper • 2408.00690 • Published Aug 1 • 21
Towards Achieving Human Parity on End-to-end Simultaneous Speech Translation via LLM Agent Paper • 2407.21646 • Published Jul 31 • 18
view article Article LAVE: Zero-shot VQA Evaluation on Docmatix with LLMs - Do We Still Need Fine-Tuning? Jul 25 • 18
view article Article ZebraLogic: Benchmarking the Logical Reasoning Ability of Language Models By yuchenlin • Jul 27 • 22
LazyLLM: Dynamic Token Pruning for Efficient Long Context LLM Inference Paper • 2407.14057 • Published Jul 19 • 44
Direct Preference Knowledge Distillation for Large Language Models Paper • 2406.19774 • Published Jun 28 • 21
VoCo-LLaMA: Towards Vision Compression with Large Language Models Paper • 2406.12275 • Published Jun 18 • 29
Simple linear attention language models balance the recall-throughput tradeoff Paper • 2402.18668 • Published Feb 28 • 18
Information Extraction Datasets Collection Collection of datasest for various information extraction tasks. • 3 items • Updated Sep 10 • 5
Universal token classification Collection Collection of universal token classification (UTC) models capable in prompt-tuned manner to solve many information extraction tasks. • 11 items • Updated Sep 10 • 12
SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities Paper • 2401.12168 • Published Jan 22 • 25
Model Merging Collection Model Merging is a very popular technique nowadays in LLM. Here is a chronological list of papers on the space that will help you get started with it! • 30 items • Updated Jun 12 • 216
WaveCoder: Widespread And Versatile Enhanced Instruction Tuning with Refined Data Generation Paper • 2312.14187 • Published Dec 20, 2023 • 49
FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness Paper • 2205.14135 • Published May 27, 2022 • 11