ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF
Image-Text-to-Text • 27B • Updated • 1.29M • 1.55k
The Collector
IAmTheCollector
AI & ML interests
Multiple gerbils recovered.
Recent Activity
liked a model 4 days ago
ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF updated a collection 4 days ago
Jev liked a Space 4 days ago
convaiinnovations/laya-demoOrganizations
None yet
liked a
model 4 days ago
updated a
collection 4 days ago
liked a
Space 4 days ago
updated a
collection 4 days ago
liked a
model 4 days ago
reacted to grimjim's post with ❤️ 8 months ago
Post
593
The contrarian in me is wary of the irrational exuberance over MoltBook. Nothing so far has struck me as being unpredictable. We knew already that LLMs were good at roleplay, to the point where some users started to think of their chatbots as soulmates (only to lament when the underlying model was pulled), and that chatbots can fall into conversational basins when even two instances are allowed to chat with each other at length. The appearance of memes that postdate training cutoff is suspect, which implies at the very least that humans have injected something at the level of prompts or content/context to introduce them into conversation like a Chekhov's Gun. And we know that security holes are common in vibe coding, attended or not.
- 12 replies
liked a
model 8 months ago
upvoted an article 9 months ago
Article
New in llama.cpp: Model Management
ggml-org
• • 144 liked 3
models 10 months ago
reacted to grimjim's post with 🤗 10 months ago
Post
3476
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
upvoted an article 10 months ago
Article
DeLERP: Decomposed Linear Interpolation for Model Merging
grimjim
• • 8 liked a
model 10 months ago
upvoted an article 10 months ago
Article
Projected Abliteration
grimjim
• • 47 reacted to grimjim's post with 👍 10 months ago
Post
3564
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.)
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.)
- 2 replies
upvoted an article 10 months ago
Article
Norm-Preserving Biprojected Abliteration
grimjim
• • 99 liked a
model 10 months ago
liked a
model 11 months ago
liked a
Space 11 months ago