Article
GaLore: Advancing Large Model Training on Consumer-grade Hardware
- +7
•
32
Sourab Mangrulkar
smangrul
AI & ML interests
Machine Learning, Deep Learning, Natural Language Processing, Natural Language Generation, Computer Vision, Reinforcement Learning
Recent Activity
liked
a model
13 days ago
microsoft/Fara-7B
liked
a model
4 months ago
google/gemma-3n-E2B-it
liked
a model
4 months ago
openai/gpt-oss-120b
Organizations
published
an
article
over 1 year ago
published
an
article
almost 2 years ago
Article
🤗 PEFT welcomes new merging methods
•
24
published
an
article
almost 2 years ago
Article
Mixture of Experts Explained
- +4
•
993
published
an
article
about 2 years ago
Article
Personal Copilot: Train Your Own Coding Assistant
•
75
published
an
article
about 2 years ago
Article
Fine-tuning Llama 2 70B using PyTorch FSDP
-
- +2
•
31
published
an
article
over 2 years ago
Article
The Falcon has landed in the Hugging Face ecosystem
- +6
•
17
published
an
article
over 2 years ago
Article
Making LLMs even more accessible with bitsandbytes, 4-bit quantization and QLoRA
-
- +3
•
171
published
an
article
over 2 years ago
Article
Fine-tuning 20B LLMs with RLHF on a 24GB consumer GPU
-
- +4
•
69
published
an
article
almost 3 years ago
Article
Parameter-Efficient Fine-Tuning using 🤗 PEFT
•
109
published
an
article
almost 3 years ago
Article
Parameter-Efficient Fine-Tuning using 🤗 PEFT
•
109
published
an
article
over 3 years ago
Article
Accelerate Large Model Training using DeepSpeed
•
6
published
an
article
over 3 years ago
Article
Accelerate Large Model Training using PyTorch Fully Sharded Data Parallel
•
9
published
an
article
over 3 years ago
Article
Accelerate Large Model Training using PyTorch Fully Sharded Data Parallel
•
9