-
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 • 4 -
The LLM Surgeon
Paper • 2312.17244 • Published • 9 -
SliceGPT: Compress Large Language Models by Deleting Rows and Columns
Paper • 2401.15024 • Published • 73
Bui Van Hop
hllj
AI & ML interests
Computer Vision, Deep Learning, NLP
Recent Activity
liked a model about 7 hours ago
Lego-X/SWE-Lego-Qwen3-8B new activity about 7 hours ago
AxiaoDBL/qwen3.5-4b-swebench-sft:What teacher model and issue pool were used for the model training? liked a model about 1 year ago
Qwen/Qwen3-30B-A3B-GPTQ-Int4Organizations
-
GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection
Paper • 2403.03507 • Published • 192 -
QA-LoRA: Quantization-Aware Low-Rank Adaptation of Large Language Models
Paper • 2309.14717 • Published • 46 -
ReFT: Representation Finetuning for Language Models
Paper • 2404.03592 • Published • 101
-
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 • 4 -
The LLM Surgeon
Paper • 2312.17244 • Published • 9 -
SliceGPT: Compress Large Language Models by Deleting Rows and Columns
Paper • 2401.15024 • Published • 73
-
GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection
Paper • 2403.03507 • Published • 192 -
QA-LoRA: Quantization-Aware Low-Rank Adaptation of Large Language Models
Paper • 2309.14717 • Published • 46 -
ReFT: Representation Finetuning for Language Models
Paper • 2404.03592 • Published • 101
models 27
hllj/paligemma-3b-mix-224-vi-llava-checkpoint-10000
Updated • 5
hllj/paligemma-3b-mix-224-vi-llava
Image-Text-to-Text • 3B • Updated • 7
hllj/mistral-instruct-v0.2-awq-marlin
Text Generation • 7B • Updated • 18
hllj/BloomZ-7B1-Vi-Math
Text Generation • 7B • Updated • 31
hllj/Qwen-7B-Vi-Math
Text Generation • 8B • Updated • 62
hllj/Zephyr-beta-7B-Vi-Math
Text Generation • 7B • Updated • 13
hllj/Llama2-7B-Vi-Math
Text Generation • 7B • Updated • 18
hllj/Mistral-7B-Vi-Math
Text Generation • 7B • Updated • 18
hllj/sft-mistral-v1-clean-valid
Updated • 12
hllj/sft-mistral-v2-clean-valid
Text Generation • Updated • 15
datasets 7
hllj/medscape
Viewer • Updated • 508 • 19 • 1
hllj/quesmed
Viewer • Updated • 4.83k • 31
hllj/synthetic-text-embedding
Viewer • Updated • 10k • 60
hllj/Vi-VLM
Updated • 5
hllj/vi_grade_school_math_mcq
Viewer • Updated • 2.73k • 68 • 4
hllj/vi_math_problem_crawl
Viewer • Updated • 10.2k • 65 • 1
hllj/vi_gsm8k
Viewer • Updated • 8.79k • 63 • 2