Thiago de Arruda Padilha

tarruda's activity

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

New activity in nex-agi/Nex-N2-mini about 9 hours ago

Very good model, punches above its weight.

#13 opened about 9 hours ago by

tarruda

New activity in nex-agi/Nex-N2-Pro about 12 hours ago

What a Monster. It is very good...

🔥 3

23

#5 opened about 1 month ago by

Hunterx

updated a model about 12 hours ago

tarruda/Hy3-GGUF

Text Generation • 295B • Updated about 12 hours ago

published a model about 13 hours ago

tarruda/Hy3-GGUF

Text Generation • 295B • Updated about 12 hours ago

updated a model 1 day ago

tarruda/Nex-N2-Pro-GGUF

Image-Text-to-Text • 396B • Updated about 14 hours ago • 474

published a model 4 days ago

tarruda/Nex-N2-Pro-GGUF

Image-Text-to-Text • 396B • Updated about 14 hours ago • 474

New activity in stepfun-ai/Step-3.7-Flash 4 days ago

Can we add something like Qwen's preserve_thinking to the chat template?

1

#15 opened 20 days ago by

tarruda

updated a model 6 days ago

tarruda/Step-3.7-Flash-GGUF

Text Generation • 197B • Updated 5 days ago • 4.8k • 10

New activity in tarruda/DeepSeek-V4-Flash-GGUF 11 days ago

Missing tensors?

5

#1 opened 12 days ago by

Mushoz

New activity in bartowski/DeepSeek-V4-Flash-GGUF 13 days ago

Gen rubbish when set -ctk q8 and -ctv q8

2

#3 opened 13 days ago by

tientitmu

updated a model 13 days ago

tarruda/DeepSeek-V4-Flash-GGUF

Text Generation • 284B • Updated 13 days ago • 5.73k • 19

published a model 14 days ago

tarruda/DeepSeek-V4-Flash-GGUF

Text Generation • 284B • Updated 13 days ago • 5.73k • 19

New activity in stepfun-ai/Step-3.7-Flash-GGUF 18 days ago

Some practical tips for using Step 3.7 GGUFs

🧠👍 2

6

#6 opened about 1 month ago by

tarruda

published a model 18 days ago

tarruda/Step-3.7-Flash-GGUF

Text Generation • 197B • Updated 5 days ago • 4.8k • 10

New activity in AesSedai/Step-3.7-Flash-GGUF 21 days ago

PPQ(Q)/PPL(base) and KLD seems significantly worse than Step 3.5 Flash

👀 1

23

#2 opened about 1 month ago by

tarruda

New activity in bartowski/prefeitura-rio_Rio-3.5-Open-397B-GGUF 26 days ago

Final model?

👍 1

7

#1 opened 30 days ago by

blankreg

updated a model 26 days ago

tarruda/Rio-3.5-Open-397B-GGUF

Text Generation • 396B • Updated 26 days ago • 901

published a model 27 days ago

tarruda/Rio-3.5-Open-397B-GGUF

Text Generation • 396B • Updated 26 days ago • 901

New activity in WithinUsAI/GPT5.5_thinking_max_distill_god_seed_25K 27 days ago

Aren't the thinking traces hidden in the OpenAI API?

1

#2 opened 27 days ago by

tarruda

New activity in nex-agi/Nex-N2-Pro 28 days ago

Model Looping in Reasoning

2

#12 opened 29 days ago by

remichu