Marc Sun's picture

Marc Sun

marcsun13

·

AI & ML interests

LLM, Quantization, Training, Inference

Recent Activity

liked a model 7 days ago

deepseek-ai/DeepSeek-V3

reacted to sayakpaul's post with 🔥 12 days ago

Commits speak louder than words 🤪 * 4 new video models * Multiple image models, including SANA & Flux Control * New quantizers -> GGUF & TorchAO * New training scripts Enjoy this holiday-special Diffusers release 🤗 Notes: https://github.com/huggingface/diffusers/releases/tag/v0.32.0

updated a model 12 days ago

hf-internal-testing/tiny-flux-dev-pipe-sharded-checkpoint-DDUF

View all activity

Articles

Introducing SynthID Text

Fine-tuning LLMs to 1.58bit: extreme quantization made easy

Accelerate 1.0.0

Llama 3.1 - 405B, 70B & 8B with multilinguality and long context

quanto: a pytorch quantization toolkit

Overview of natively supported quantization schemes in 🤗 Transformers

Making LLMs lighter with AutoGPTQ and transformers

Organizations

marcsun13's activity

liked a model 7 days ago

deepseek-ai/DeepSeek-V3

Updated 16 days ago • 132k • 1.87k

liked a Space 2 months ago

BitNet.cpp

liked 2 Spaces 3 months ago

Running on L40S

SynthID Text

Watermarking LLM-generated text with SynthID Text

Running on A100

QuantizationTorchAODraft

liked 3 models 4 months ago

HF1BitLLM/Llama3-8B-1.58-Sigmoid-k100-10B-tokens

Text Generation • Updated Sep 18, 2024 • 21 • 10

HF1BitLLM/Llama3-8B-1.58-Linear-10B-tokens

Text Generation • Updated Sep 18, 2024 • 232 • 9

HF1BitLLM/Llama3-8B-1.58-100B-tokens

Text Generation • Updated Sep 19, 2024 • 1.87k • 167

liked a Space 4 months ago

Mapping the AI OS community

liked a Space 5 months ago

Wllama

Run GGUF directly on your browser!

liked a model 6 months ago

meta-llama/Llama-3.1-405B-Instruct-FP8

Text Generation • Updated Sep 25, 2024 • 13.9k • 183

liked 2 models 7 months ago

google/gemma-2-9b

Text Generation • Updated Aug 7, 2024 • 98.9k • 627

neuralmagic/Meta-Llama-3-8B-Instruct-FP8

Text Generation • Updated Jul 18, 2024 • 9.57k • 18

liked a model 8 months ago

ISTA-DASLab/Meta-Llama-3-8B-AQLM-PV-2Bit-1x16

Text Generation • Updated May 31, 2024 • 95 • 3

liked 4 models 9 months ago

meta-llama/Meta-Llama-3-70B-Instruct

Text Generation • Updated Dec 15, 2024 • 48.2k • • 1.45k

meta-llama/Meta-Llama-3-8B-Instruct

Text Generation • Updated Sep 27, 2024 • 1.51M • • 3.76k

meta-llama/Meta-Llama-3-8B

Text Generation • Updated Sep 27, 2024 • 471k • 5.97k

mistralai/Mixtral-8x22B-v0.1

Text Generation • Updated Oct 3, 2024 • 2.99M • 208

liked a model 10 months ago

google/flan-t5-xxl

Text2Text Generation • Updated Jul 27, 2023 • 660k • 1.23k

liked 2 Spaces 11 months ago

Compute Pipeline Size

Running on CPU Upgrade

LoRA Studio

Browse and run thousands of community trained LoRAs