9 2 7

Serveurperso PRO

Serveurperso

https://www.serveurperso.com

ServeurpersoCom

AI & ML interests

None yet

Recent Activity

liked a model 3 days ago

Aryanne/acestep-v15-test-merges

liked a model 3 days ago

ACE-Step/acestep-transcriber

liked a model 3 days ago

ACE-Step/acestep-captioner

View all activity

Organizations

liked 3 models 3 days ago

upvoted an article 6 days ago

Article

GGML and llama.cpp join HF to ensure the long-term progress of Local AI

19 days ago

•

480

New activity in Serveurperso/ACE-Step-1.5-GGUF 11 days ago

The 1.7B LM models are incorrectly converted

👍 1

#1 opened 14 days ago by

concedo

updated a model 11 days ago

Serveurperso/ACE-Step-1.5-GGUF

0.7B • Updated 11 days ago • 7.96k • 20

commented on GGML and llama.cpp join HF to ensure the long-term progress of Local AI 13 days ago

A great milestone for Local AI!
For those already living daily in the ggml and llama.cpp ecosystem, this is a strong signal for what’s ahead.
The alignment with Transformers brings clear strategic coherence.
A solid move. Looking forward to what comes next.

published a model 19 days ago

Serveurperso/ACE-Step-1.5-GGUF

0.7B • Updated 11 days ago • 7.96k • 20

New activity in unsloth/GLM-4.7-REAP-218B-A32B-GGUF about 2 months ago

Repeats a single word or phrase endlessly every single time I try to prompt

#1 opened about 2 months ago by

Disdrix

updated a model about 2 months ago

Serveurperso/presets

Updated Jan 10

published a model about 2 months ago

Serveurperso/presets

Updated Jan 10

New activity in huggingface/HuggingDiscussions about 2 months ago

[FEEDBACK] Local apps

👀 ❤️ 4

#31 opened almost 2 years ago by

kramp

reacted to ngxson's post with 🚀 2 months ago

Post

6135

A comprehensive matrix for which format should you use.

Read more on my blog post: https://huggingface.co/blog/ngxson/common-ai-model-formats

| Hardware        | GGUF      | PyTorch                | Safetensors              | ONNX  |
|-----------------|-----------|------------------------|--------------------------|-------|
| CPU             | ✅ (best) | 🟡                      | 🟡                       | ✅    |
| GPU             | ✅        | ✅                      | ✅                       | ✅    |
| Mobile          | ✅        | 🟡 (via executorch)     | ❌                       | ✅    |
| Apple silicon   | ✅        | 🟡                      | ✅ (via MLX framework)   | ✅    |

1 reply

liked a Space 4 months ago

Robot Learning: A Tutorial

📝

349

Explore the Robot Learning tutorial online

reacted to grimjim's post with 👍 4 months ago

Post

3425

Going forward, I will be adopting the term Magnitude-Preserving Orthogonal Ablation (MPOA) for my recent work in mitigating model damage from abliteration. The technique potentially unlocks reasoning capacity previously occupied with safety refusal processing.

For details, start here: https://huggingface.co/blog/grimjim/norm-preserving-biprojected-abliteration

Showcase results: grimjim/gemma-3-12b-it-norm-preserved-biprojected-abliterated (outperforms base instruct on UGI Leaderboard NatInt)

(The existing name, while technically accurate, was a bit of a mouthful.)