Marc Sun's picture

Marc Sun

marcsun13

·

AI & ML interests

LLM, Quantization, Training, Inference

Recent Activity

new activity about 7 hours ago

hf-accelerate/model-memory-usage:Error accessing Llama4 models: 'does not have any library metadata on the Hub'

new activity about 7 hours ago

hf-accelerate/model-memory-usage:GPTQ group size effects vRAM usage

new activity about 7 hours ago

hf-accelerate/model-memory-usage:Determining Minimum GPU Memory and Input Text Length Calculation in Model Training

View all activity

Organizations

Articles 8

Article

53

LLM Inference on Edge: A Fun and Easy Guide to run LLMs via React Native on your Phone!

Article

42

Introducing SynthID Text

View all Articles

models 19

marcsun13/Llama-3.1-8B-Instruct-bnb-4bit

Text Generation • Updated Mar 20 • 4

marcsun13/phi-4-bnb-4bit

Text Generation • Updated Mar 18 • 2

marcsun13/Llama-3.2-1B-bnb-4bit

Text Generation • Updated Mar 18 • 2

marcsun13/Llama-3.2-1B-Instruct-SpinQuant_INT4_EO8

Updated Feb 13 • 3

marcsun13/paligemma_vqav2

marcsun13/Meta-Llama-3-8B-torchao-int8_weight_only

Updated Oct 18, 2024

marcsun13/sft_openassistant-guanaco

Text Generation • Updated Jul 5, 2024 • 2

marcsun13/gemma-2-27b-it-bnb-colab

Text Generation • Updated Jul 4, 2024 • 1

marcsun13/gemma-2-9b-it-GPTQ

Text Generation • Updated Jul 3, 2024 • 420 • 3

marcsun13/test_push_checkpoint

Fill-Mask • Updated Jun 28, 2024 • 2

datasets 0

None public yet