guiferrarib/genesis-152m-instruct
Text Generation
•
Updated
•
8
Yazan Agha-Schrader PRO
phi0112358
AI & ML interests
Brain, EEG, BCI, consciousness, autism, octopus, automation, a.i., etymology, numbers, spirituality, astronomy
Recent Activity
liked
a model
1 day ago
guiferrarib/genesis-152m-instruct
liked
a model
3 days ago
unsloth/Z-Image-Turbo-GGUF
liked
a model
10 days ago
ggml-org/functiongemma-270m-it-GGUF
Organizations
liked
a
model
1 day ago
liked
a
model
3 days ago
liked
2
models
10 days ago
liked
a
dataset
19 days ago
liked
a
model
19 days ago
liked
a
model
20 days ago
upvoted
an
article
24 days ago
Article
We Got Claude to Fine-Tune an Open Source LLM
•
541
updated
a
model
24 days ago
liked
a
model
25 days ago
published
a
model
25 days ago
liked
a
model
26 days ago
reacted to
grimjim's
post with 🤗
26 days ago
Post
3111
I wanted to call attention to Arli Ai's success in applying my recent modifications to refusal ablation to a MoE model successfully. Nice work,
@OwenArli
!
ArliAI/GLM-4.5-Air-Derestricted
Ablation on a MoE model is no small thing; I expect preserving norms/magnitudes during intervention better respects routing compared to naive refusal ablation.
(I would have tagged their org earlier, but that feature seemed to be broken via "@")
ArliAI
ArliAI/GLM-4.5-Air-Derestricted
Ablation on a MoE model is no small thing; I expect preserving norms/magnitudes during intervention better respects routing compared to naive refusal ablation.
(I would have tagged their org earlier, but that feature seemed to be broken via "@")
- 4 replies
updated
a
model
26 days ago
published
a
model
26 days ago
updated
a
model
26 days ago
published
a
model
26 days ago
upvoted
an
article
26 days ago
Article
Norm-Preserving Biprojected Abliteration
•
56
updated
a
model
26 days ago
published
a
model
26 days ago