-
ShortGPT: Layers in Large Language Models are More Redundant Than You Expect
Paper • 2403.03853 • Published • 66 -
SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot
Paper • 2301.00774 • Published • 3 -
The LLM Surgeon
Paper • 2312.17244 • Published • 9 -
SliceGPT: Compress Large Language Models by Deleting Rows and Columns
Paper • 2401.15024 • Published • 75
Bui Van Hop
hllj
AI & ML interests
Computer Vision, Deep Learning, NLP
Recent Activity
liked
a model
4 days ago
Qwen/Qwen3-30B-A3B-GPTQ-Int4
liked
a Space
4 days ago
Qwen/Qwen3-Demo
liked
a dataset
about 1 month ago
Skylion007/openwebtext
Organizations
-
GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection
Paper • 2403.03507 • Published • 189 -
QA-LoRA: Quantization-Aware Low-Rank Adaptation of Large Language Models
Paper • 2309.14717 • Published • 44 -
ReFT: Representation Finetuning for Language Models
Paper • 2404.03592 • Published • 100
-
ShortGPT: Layers in Large Language Models are More Redundant Than You Expect
Paper • 2403.03853 • Published • 66 -
SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot
Paper • 2301.00774 • Published • 3 -
The LLM Surgeon
Paper • 2312.17244 • Published • 9 -
SliceGPT: Compress Large Language Models by Deleting Rows and Columns
Paper • 2401.15024 • Published • 75
-
GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection
Paper • 2403.03507 • Published • 189 -
QA-LoRA: Quantization-Aware Low-Rank Adaptation of Large Language Models
Paper • 2309.14717 • Published • 44 -
ReFT: Representation Finetuning for Language Models
Paper • 2404.03592 • Published • 100
models
27
hllj/paligemma-3b-mix-224-vi-llava-checkpoint-10000
Updated
•
3
hllj/paligemma-3b-mix-224-vi-llava
Image-to-Text
•
3B
•
Updated
•
4
hllj/mistral-instruct-v0.2-awq-marlin
Text Generation
•
1B
•
Updated
•
4
hllj/BloomZ-7B1-Vi-Math
Text Generation
•
7B
•
Updated
•
7
hllj/Qwen-7B-Vi-Math
Text Generation
•
8B
•
Updated
•
5
hllj/Zephyr-beta-7B-Vi-Math
Text Generation
•
7B
•
Updated
•
3
hllj/Llama2-7B-Vi-Math
Text Generation
•
7B
•
Updated
•
3
hllj/Mistral-7B-Vi-Math
Text Generation
•
7B
•
Updated
•
9
hllj/sft-mistral-v1-clean-valid
Updated
•
4
hllj/sft-mistral-v2-clean-valid
Text Generation
•
Updated
•
4
datasets
7
hllj/medscape
Viewer
•
Updated
•
508
•
7
•
1
hllj/quesmed
Viewer
•
Updated
•
4.83k
•
8
hllj/synthetic-text-embedding
Viewer
•
Updated
•
10k
•
59
hllj/Vi-VLM
Updated
•
2
hllj/vi_grade_school_math_mcq
Viewer
•
Updated
•
2.73k
•
24
•
3
hllj/vi_math_problem_crawl
Viewer
•
Updated
•
10.2k
•
27
•
1
hllj/vi_gsm8k
Viewer
•
Updated
•
8.79k
•
25
•
2