tencent/HunyuanVideo-1.5
Text-to-Video
ā¢
Updated
ā¢
2.69k
ā¢
ā¢
796
Bot PRO
inflatebot
AI & ML interests
"Potentially one of my biggest flaws is that I genuinely think that the science appreciates when you commit to a bit." - Tom ExtractionsAndIre
Recent Activity
liked
a model
12 days ago
tencent/HunyuanVideo-1.5
new activity
15 days ago
cathuriges/tigerlily-r3:Created a GGUF/Quantized version for you guys
updated
a model
16 days ago
cathuriges/tigerlily-r3
Organizations
liked
a
model
12 days ago
Created a GGUF/Quantized version for you guys
ā¤ļø
1
4
#1 opened 15 days ago
by
EnlistedGhost
updated
2
models
16 days ago
published
2
models
16 days ago
updated
a
model
16 days ago
published
a
model
16 days ago
reacted to
grimjim's
post with š
16 days ago
Post
3253
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
reacted to
ZennyKenny's
post with š„
16 days ago
reacted to
grimjim's
post with š„
18 days ago
Post
5009
Implemented a proof of concept sampler in pure PyTorch and transformers.
Max P consists of a dynamic token filter which applies Winsorization to cap the probabilties of top tokens. Specifically, a base probability in the range of [0,1] is used to cap individual token probability; the sampler then redistributes excess proportionally.
https://github.com/jim-plus/maxp-sampler-poc
Combined with Temperature and Min P, this could represent a more intuitive way of reducing repetition in text generation.
Max P consists of a dynamic token filter which applies Winsorization to cap the probabilties of top tokens. Specifically, a base probability in the range of [0,1] is used to cap individual token probability; the sampler then redistributes excess proportionally.
https://github.com/jim-plus/maxp-sampler-poc
Combined with Temperature and Min P, this could represent a more intuitive way of reducing repetition in text generation.
- 2 replies
updated
a
model
18 days ago
License?
3
#17 opened 19 days ago
by
rosethelocalfem
updated
a
model
19 days ago
published
a
model
19 days ago
updated
a
model
19 days ago
published
2
models
19 days ago
liked
a
model
24 days ago
replied to
their
post
24 days ago
I would like to make a merge of that size, but unfortunately I haven't found any of the Mistrals to be useful; there are seemingly-intractable problems with the architecture that foil every attempt to make it not repeat the same paragraph over and over, even on OpenRouter where my PC ceases to be a factor. (But like, people like them!! So maybe I have a skill issue, who knows!)
Even if I did, though, it wouldn't be "Mag Mell" exactly. There aren't any similar reagents; especially not since Anthracite evaporated and crestf4ll disappeared.
Of a similar philosophy though, absolutely.
I've been focusing on my physical/mental health this year, and I finally got a family doctor since I posted this so I hope to be active again before too much longer.
Right now I'm experimenting with Gemma3-12B, because for a 12B it's very capable (and I like multimodal models,) and Grimjim's projection-abliteration experiment leads me to believe that I can make it do what I want.
So stay tuned, I suppose. Idk. Primarily I do stuff for me, and I'm trying to get back to that. :P