12 15 11

gaochangkuan

https://github.com/ScottishFold007

ScottishFold

AI & ML interests

NLP；文本挖掘

Recent Activity

new activity 17 days ago

facebook/sam3:cannot access to this model

upvoted an article 27 days ago

What makes good reasoning data

new activity about 2 months ago

cpatonn/Qwen3-Omni-30B-A3B-Instruct-AWQ-8bit:size mismatch for weight_packed: copying a param with shape torch.Size([2048, 192]) from checkpoint, the shape in current model is torch.Size([2048, 96]).

View all activity

Organizations

New activity in facebook/sam3 17 days ago

cannot access to this model

🔥 👍 10

#7 opened 17 days ago by

6chan

upvoted an article 27 days ago

Article

What makes good reasoning data

Oct 30

•

New activity in cpatonn/Qwen3-Omni-30B-A3B-Instruct-AWQ-8bit about 2 months ago

size mismatch for weight_packed: copying a param with shape torch.Size([2048, 192]) from checkpoint, the shape in current model is torch.Size([2048, 96]).

#1 opened about 2 months ago by

gaochangkuan

upvoted an article 4 months ago

Article

What I Learned Upscaling a Long-distance Midjourney Photo w/ Stable Diffusion PLUS unboxing Qwen Image & Wan 2.2

Aug 8

•

commented a paper 5 months ago

Should We Still Pretrain Encoders with Masked Language Modeling?

Paper • 2507.00994 • Published Jul 1 • 79 •

upvoted an article 5 months ago

Article

Training and Finetuning Sparse Embedding Models with Sentence Transformers v5

Jul 1

•

130

upvoted 4 articles 6 months ago

Article

Learn the Hugging Face Kernel Hub in 5 Minutes

Jun 12

•

151

Article

The Great Debate: Should AI Feel Fear Like Humans?

Jun 16

•

Article

Bond Capital 2025年AI趋势报告解读

Jun 8

•

Article

MCP is at a Tipping Point: Here's Why You Should Care

Jun 10

•

upvoted 2 articles 7 months ago

Article

Open-source DeepResearch – Freeing our search agents

Feb 4

•

1.31k

Article

Page-to-Video: Generate videos from webpages 🪄🎬

May 6

•

upvoted an article 8 months ago

Article

Are AI Agents Sustainable? It depends

Apr 7

•

liked a Space 10 months ago

The Ultra-Scale Playbook

🌌

3.55k

The ultimate guide to training LLM on large GPU Clusters

upvoted an article 10 months ago

Article

From Llasa to Llasagna 🍕: Finetuning LLaSA to generates Italian speech and other languages

Feb 11

•

liked a dataset 10 months ago

HKUSTAudio/Llasa_opensource_speech_data_160k_hours_tokenized

Updated Feb 13 • 521 • 30

upvoted 2 articles 10 months ago

Article

From Zero to Reasoning Hero: How DeepSeek-R1 Leverages Reinforcement Learning to Master Complex Reasoning

Feb 4

•

Article

Open-R1: Update #1

Feb 2

•

305

liked a Space 11 months ago

Make Custom Voices With KokoroTTS

⚡

124

Make Custom Voices With KokoroTTS

updated a model about 1 year ago

gaochangkuan/whisper-large-v2_FT_model_checkpoints

Automatic Speech Recognition • 2B • Updated Sep 29, 2024 • 4

gaochangkuan

AI & ML interests

Recent Activity

Organizations

gaochangkuan's activity

cannot access to this model

What makes good reasoning data

size mismatch for weight_packed: copying a param with shape torch.Size([2048, 192]) from checkpoint, the shape in current model is torch.Size([2048, 96]).

What I Learned Upscaling a Long-distance Midjourney Photo w/ Stable Diffusion PLUS unboxing Qwen Image & Wan 2.2

Training and Finetuning Sparse Embedding Models with Sentence Transformers v5

Learn the Hugging Face Kernel Hub in 5 Minutes

The Great Debate: Should AI Feel Fear Like Humans?

Bond Capital 2025年AI趋势报告解读

MCP is at a Tipping Point: Here's Why You Should Care

Open-source DeepResearch – Freeing our search agents

Page-to-Video: Generate videos from webpages 🪄🎬

Are AI Agents Sustainable? It depends

The Ultra-Scale Playbook

From Llasa to Llasagna 🍕: Finetuning LLaSA to generates Italian speech and other languages

From Zero to Reasoning Hero: How DeepSeek-R1 Leverages Reinforcement Learning to Master Complex Reasoning

Open-R1: Update #1

Make Custom Voices With KokoroTTS