Erik

Tralalabs's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

updated a dataset 4 days ago

Tralalabs/qwen3-coder-480b-85xx

Viewer • Updated 4 days ago • 85 • 8

published a dataset 4 days ago

Tralalabs/qwen3-coder-480b-85xx

Viewer • Updated 4 days ago • 85 • 8

New activity in google/gemma-3-27b-it 4 days ago

Please release now Gemma 3.5

3

#101 opened 4 days ago by

Tralalabs

updated a Space 5 days ago

Sleeping

Tralalabs Space

⚡

A Hugging Face Space powered by Qwen2.5 1.5B 👌

published a Space 5 days ago

Sleeping

Tralalabs Space

⚡

A Hugging Face Space powered by Qwen2.5 1.5B 👌

New activity in google/gemma-3-27b-it 7 days ago

Status on Gemma 4?

🔥 6

3

#100 opened 9 days ago by

Dampfinchen

liked 2 models 7 days ago

ggml-org/gemma-3-1b-it-GGUF

1.0B • Updated Mar 12, 2025 • 14.6k • 26

lmstudio-community/gemma-3-1b-it-GGUF

Text Generation • 1.0B • Updated Mar 12, 2025 • 2.46k • 7

liked a Space 8 days ago

Running

6

OpenClaw Gateway

🦞

6

Control your OpenClaw robot from a web dashboard

updated a model 9 days ago

Tralalabs/Orca-Nano-G3

0.6B • Updated 9 days ago • 68

published a model 9 days ago

Tralalabs/Orca-Nano-G3

0.6B • Updated 9 days ago • 68

updated a model 9 days ago

Tralalabs/Smalan-270M-GGUF

0.3B • Updated 9 days ago • 30

published a model 9 days ago

Tralalabs/Smalan-270M-GGUF

0.3B • Updated 9 days ago • 30

updated a model 12 days ago

Tralalabs/HighThinker-4B-LoRA

Text Generation • Updated 12 days ago • 9

published a model 12 days ago

Tralalabs/HighThinker-4B-LoRA

Text Generation • Updated 12 days ago • 9

reacted to danielhanchen's post with 🔥 15 days ago

view post

Post

5145

We collaborated with Hugging Face to enable you to train MoE models 12× faster with 35% less VRAM via our new Triton kernels (no accuracy loss). 🤗

Train gpt-oss locally on 12.8GB VRAM with our free notebooks: https://unsloth.ai/docs/new/faster-moe

See translation

• 
• 

• 
• 1 reply

·

🔥

29

29

🤗

5

5

+

Reply

liked a model 16 days ago

openbmb/MiniCPM-o-4_5

Any-to-Any • 9B • Updated 1 day ago • 91.4k • 880

New activity in Tralalabs/Nora-4B-LoRA 18 days ago

I trained LoRA adapters for Qwen3-4B using Unsloth on mixed instruction data. I’m looking for feedback on instruction following and stability.

#1 opened 18 days ago by

Tralalabs

liked a model 18 days ago

Tralalabs/Nora-4B-LoRA

Updated 18 days ago • 1

updated a model 18 days ago

Tralalabs/Nora-4B-LoRA

Updated 18 days ago • 1