-
The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits
Paper • 2402.17764 • Published • 615 -
Beyond Language Models: Byte Models are Digital World Simulators
Paper • 2402.19155 • Published • 54 -
BitNet v2: Native 4-bit Activations with Hadamard Transformation for 1-bit LLMs
Paper • 2504.18415 • Published • 41
kas
shing3232
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
8 days ago
TransMLA: Multi-head Latent Attention Is All You Need
updated
a collection
12 days ago
sakura
upvoted
an
article
21 days ago
Fine-tuning LLMs to 1.58bit: extreme quantization made easy
Organizations
None yet
Collections
1
models
9
shing3232/Sakura-1.5B-Qwen2.5-v1.0-GGUF-IMX
Updated
•
32
•
1
shing3232/sakura-14b-qwen2beta-v0.9.2-IMX
Updated
•
7
•
3
shing3232/Sakura13B-LNovel-v0.9-qwen1.5-GGUF-IMX
Updated
•
37
•
7
shing3232/Sakura1.8B-LNovel-v0.9pre2-qwen1_GGUF-IMX
Updated
•
18
shing3232/Sakura13B-LNovel-v0.9b-GGUF-IMX-2.33_re
Updated
•
10
shing3232/Sakura1.8B-LNovel-v0.9-qwen1.5_GGUF-IMX_re
Updated
•
13
•
1
shing3232/Sakura13B-LNovel-v0.9b-GGUF-IMX-2.33
Updated
•
79
•
3
shing3232/Sakura-LNovel-v0.9b-GGUF-IMX-JPZH
Updated
•
307
shing3232/Sakura-13B-LNovel-v0.9b-GGUF-IMX-wikitest
Updated
•
6