Chenhui Zhang PRO

danielz01's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a collection 12 months ago

Meta Llama 3

Collection

This collection hosts the transformers and original repos of the Meta Llama 3 and Llama Guard 2 releases • 5 items • Updated Dec 6, 2024 • 749

upvoted 2 papers about 1 year ago

Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference

Paper • 2403.04132 • Published Mar 7, 2024 • 41

DataDreamer: A Tool for Synthetic Data Generation and Reproducible LLM Workflows

Paper • 2402.10379 • Published Feb 16, 2024 • 32

upvoted 2 collections about 1 year ago

🔍 Interpretability & Analysis of LMs

Collection

Outstanding research in LM interpretability and evaluation, summarized • 107 items • Updated 10 days ago • 99

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, 2024 • 236

upvoted a paper about 1 year ago

SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities

Paper • 2401.12168 • Published Jan 22, 2024 • 28

upvoted 6 papers over 1 year ago

Interfacing Foundation Models' Embeddings

Paper • 2312.07532 • Published Dec 12, 2023 • 15

LM-Infinite: Simple On-the-Fly Length Generalization for Large Language Models

Paper • 2308.16137 • Published Aug 30, 2023 • 40

SparQ Attention: Bandwidth-Efficient LLM Inference

Paper • 2312.04985 • Published Dec 8, 2023 • 40

GIVT: Generative Infinite-Vocabulary Transformers

Paper • 2312.02116 • Published Dec 4, 2023 • 13

The CoT Collection: Improving Zero-shot and Few-shot Learning of Language Models via Chain-of-Thought Fine-Tuning

Paper • 2305.14045 • Published May 23, 2023 • 5

Vision Transformers Need Registers

Paper • 2309.16588 • Published Sep 28, 2023 • 80

upvoted a collection over 1 year ago

Switch-Transformers release

Collection

This release included various MoE (Mixture of expert) models, based on the T5 architecture . The base models use from 8 to 256 experts. • 9 items • Updated 20 days ago • 17

upvoted 6 papers over 1 year ago

I&S-ViT: An Inclusive & Stable Method for Pushing the Limit of Post-Training ViTs Quantization

Paper • 2311.10126 • Published Nov 16, 2023 • 10

FlashFFTConv: Efficient Convolutions for Long Sequences with Tensor Cores

Paper • 2311.05908 • Published Nov 10, 2023 • 16

Mirasol3B: A Multimodal Autoregressive model for time-aligned and contextual modalities

Paper • 2311.05698 • Published Nov 9, 2023 • 14

PolyMaX: General Dense Prediction with Mask Transformer

Paper • 2311.05770 • Published Nov 9, 2023 • 11

Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks

Paper • 2311.06242 • Published Nov 10, 2023 • 93

Parameter-Efficient Orthogonal Finetuning via Butterfly Factorization

Paper • 2311.06243 • Published Nov 10, 2023 • 22