Shyam Peri

shyamperi's activity

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

upvoted a paper 11 days ago

Evaluating Language Models as Synthetic Data Generators

Paper • 2412.03679 • Published 13 days ago • 43

upvoted a collection 13 days ago

Finance Commons

Collection

A large collection of multimodal financial documents in open data. • 7 items • Updated Jul 17 • 7

liked a model 19 days ago

Qwen/QwQ-32B-Preview

Text Generation • Updated 19 days ago • 110k • • 1.32k

upvoted a collection 21 days ago

OLMo 2

Collection

Artifacts for the second set of OLMo models. • 17 items • Updated 20 days ago • 54

liked a Space 29 days ago

Running on T4

41

👀

ColPali 🤝 Vespa - Visual Retrieval

Visual Retrieval with ColPali and Vespa

upvoted a collection about 2 months ago

Llama 3.2

Collection

This collection hosts the transformers and original repos of the Llama 3.2 and Llama Guard 3 • 15 items • Updated 12 days ago • 543

liked a Space about 2 months ago

Running

25

🥐

Croissant Editor

upvoted a collection about 2 months ago

MedEmbed: Embedding Models for Medical Domain

Collection

GitHub -> https://github.com/abhinand5/MedEmbed • 4 items • Updated Oct 21 • 9

liked a Space about 2 months ago

Running

2

📊

CareerPath

liked 2 models 2 months ago

HF1BitLLM/Llama3-8B-1.58-100B-tokens

Text Generation • Updated Sep 19 • 4.76k • 165

1bitLLM/bitnet_b1_58-large

Text Generation • Updated Mar 29 • 5.21k • 77

liked a dataset 2 months ago

mlabonne/open-perfectblend

Viewer • Updated Oct 18 • 1.42M • 159 • 45

liked 3 models 2 months ago

jxm/cde-small-v1

Feature Extraction • Updated Oct 30 • 14.4k • 282

dell-research-harvard/wire-classifier

Text Classification • Updated Aug 15 • 14 • 2

arzuhussein/atllama

Updated Oct 4 • 6 • 3

upvoted a paper 3 months ago

Addition is All You Need for Energy-efficient Language Models

Paper • 2410.00907 • Published Oct 1 • 144

liked a Space 3 months ago

Running on T4

1.01k

🎙️

Open NotebookLM

Personalised Podcasts For All - Available in 13 Languages

upvoted a paper 3 months ago

Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Experts

Paper • 2409.16040 • Published Sep 24 • 12

upvoted a collection 3 months ago

DataGemma Release

Collection

A series of pioneering open models that help ground LLMs in real-world data through Data Commons. • 2 items • Updated 4 days ago • 81

liked a model 3 months ago

microsoft/GRIN-MoE

Text Generation • Updated Sep 19 • 241 • 194