Shuming Ma

shumingma's activity

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

authored a paper 7 days ago

BitNet v2: Native 4-bit Activations with Hadamard Transformation for 1-bit LLMs

Paper • 2504.18415 • Published 11 days ago • 41

New activity in microsoft/bitnet-b1.58-2B-4T 8 days ago

Eval numbers for Llama 3.2 1B in Table 1 don't match Meta's results

3

#28 opened 8 days ago by

AlexA5432

New activity in microsoft/bitnet-b1.58-2B-4T 12 days ago

Important confirmation: about the deviation from the model that was originally uploaded

5

#12 opened 18 days ago by

AXCXEPT

upvoted 2 papers 17 days ago

BitNet: Scaling 1-bit Transformers for Large Language Models

Paper • 2310.11453 • Published Oct 17, 2023 • 102

BitNet b1.58 2B4T Technical Report

Paper • 2504.12285 • Published 19 days ago • 70

New activity in microsoft/bitnet-b1.58-2B-4T-gguf 18 days ago

gguf not llama.cpp compatible yet

3

#2 opened 20 days ago by

lefromage

New activity in microsoft/bitnet-b1.58-2B-4T 18 days ago

Missing configuration_bitnet.py.

6

5

#9 opened 18 days ago by

here4code

authored a paper 19 days ago

BitNet b1.58 2B4T Technical Report

Paper • 2504.12285 • Published 19 days ago • 70

New activity in microsoft/bitnet-b1.58-2B-4T 19 days ago

configuration_bitnet.py missing

8

15

#4 opened 20 days ago by

lefromage

Technical Report Link Missing

1

#1 opened 20 days ago by

G-reen

upvoted a collection 19 days ago

BitNet

Collection

🔥BitNet family of large language models (1-bit LLMs). • 7 items • Updated 5 days ago • 35

liked 3 models 20 days ago

microsoft/bitnet-b1.58-2B-4T-gguf

Text Generation • Updated 5 days ago • 31.8k • 158

microsoft/bitnet-b1.58-2B-4T-bf16

Text Generation • Updated 5 days ago • 3.37k • 25

microsoft/bitnet-b1.58-2B-4T

Text Generation • Updated 5 days ago • 50k • 936

authored 2 papers 5 months ago

BitNet a4.8: 4-bit Activations for 1-bit LLMs

Paper • 2411.04965 • Published Nov 7, 2024 • 69

MH-MoE:Multi-Head Mixture-of-Experts

Paper • 2411.16205 • Published Nov 25, 2024 • 28

upvoted a paper 6 months ago

BitNet a4.8: 4-bit Activations for 1-bit LLMs

Paper • 2411.04965 • Published Nov 7, 2024 • 69

commented a paper 7 months ago

The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits

Paper • 2402.17764 • Published Feb 27, 2024 • 615 •

143

upvoted an article 8 months ago

view article

Article

Fine-tuning LLMs to 1.58bit: extreme quantization made easy

Sep 18, 2024

• 242

upvoted a paper 10 months ago

Q-Sparse: All Large Language Models can be Fully Sparsely-Activated

Paper • 2407.10969 • Published Jul 15, 2024 • 23