Tyler Williams PRO

unmodeled-tyler's activity

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

reacted to danielhanchen's post with 🔥 about 1 hour ago

view post

Post

81

You can now run MiniMax-2.5 locally! 🚀
At 230B parameters, MiniMax-2.5 is the strongest LLM under 700B params, delivering SOTA agentic coding & chat.

Run Dynamic 3/4-bit on a 128GB Mac for 20 tokens/s.
Guide: https://unsloth.ai/docs/models/minimax-2.5
GGUF: unsloth/MiniMax-M2.5-GGUF

See translation

• 
• 

🔥

1

1

+

Reply

replied to Ujjwal-Tyagi's post 3 days ago

view reply

I've been using it quite a bit lately. Really been enjoying it so far!

reacted to EricFillion's post with 🔥 3 days ago

view post

Post

3545

Run open-source models with up to 120B parameters locally on your Mac!

https://youtu.be/Ql4PDjoxNXQ?si=3yHpz51uinUjgyNh

See translation

• 

• 
• 
• 2 replies

·

🔥

9

9

+

Reply

updated a collection 4 days ago

Recommended Papers

Collection

Curated collection of research papers that I think are worth sharing or find particularly interesting. • 6 items • Updated 4 days ago

updated 9 models 6 days ago

vanta-research/atom-80b

Text Generation • 80B • Updated 6 days ago • 133 • 12

vanta-research/atom-27b

Text Generation • 27B • Updated 6 days ago • 443 • 10

vanta-research/atom-v1-preview-4b

Text Generation • 4B • Updated 6 days ago • 1.67k • 8

vanta-research/scout-4b

Text Generation • 4B • Updated 6 days ago • 2.9k • 15

vanta-research/PE-Type-3-Nova-4B

Image-Text-to-Text • 4B • Updated 6 days ago • 251 • 1

vanta-research/PE-Type-2-Alma-4B

Image-Text-to-Text • 4B • Updated 6 days ago • 235 • 5

vanta-research/PE-Type-1-Vera-4B

Image-Text-to-Text • 4B • Updated 6 days ago • 1.19k • 3

vanta-research/mox-tiny-1

Text Generation • 8B • Updated 6 days ago • 387 • 18

vanta-research/wraith-8b

Text Generation • 8B • Updated 6 days ago • 989 • 8

updated 4 models 8 days ago

vanta-research/atom-olmo3-7b

Text Generation • 7B • Updated 8 days ago • 214 • 5

vanta-research/apollo-astralis-4b

Text Generation • 4B • Updated 8 days ago • 90 • 6

vanta-research/mox-small-1

32B • Updated 8 days ago • 105 • 4

vanta-research/atom-v1-preview-8b

Text Generation • 8B • Updated 8 days ago • 386 • 4

reacted to efecelik's post with 🔥 10 days ago

view post

Post

3028

The moment we've been waiting for — ACE-Step dropped their new model: Ace-Step 1.5 🎉
🔗 ACE-Step/Ace-Step1.5
And the best part? It's released under the MIT license.
We've already started integrating it into our project. Let's go 🚀

See translation

• 
• 1 reply

·

🔥

6

6

🚀

1

1

+

Reply

reacted to their post with 🚀 10 days ago

view post

Post

352

NEW MODEL: vanta-research/PE-Type-3-Nova-4B

PE-Type-3-Nova-4B is the 3rd release in Project Enneagram, an initiative from VANTA Research that sets out to finetune each of the 9 Enneagram types onto Gemma 3 4B.

Type-3-Nova-4B is designed to embody the Type 3 or "Achiever" profile; ambitious, competent, energetic, and highly-driven for advancement.

Nova is great for goal-setting, long-term planning, and AI persona research.

Give Type-3 a try! Type-4 coming soon!

See translation

🚀

2

2

+

Reply

posted an update 10 days ago

view post

Post

352

NEW MODEL: vanta-research/PE-Type-3-Nova-4B

PE-Type-3-Nova-4B is the 3rd release in Project Enneagram, an initiative from VANTA Research that sets out to finetune each of the 9 Enneagram types onto Gemma 3 4B.

Type-3-Nova-4B is designed to embody the Type 3 or "Achiever" profile; ambitious, competent, energetic, and highly-driven for advancement.

Nova is great for goal-setting, long-term planning, and AI persona research.

Give Type-3 a try! Type-4 coming soon!

See translation

🚀

2

2

+

Reply