MiniMaxAI/MiniMax-M2.1
Text Generation
•
229B
•
Updated
•
60k
•
•
525
Djuunaa
djuna
AI & ML interests
None yet
Recent Activity
new activity
3 days ago
Lambent/IsoC-Gemma-3-12B:Weight = 1.0?
liked
a model
3 days ago
MiniMaxAI/MiniMax-M2.1
liked
a model
10 days ago
schneewolflabs/A0l-12B
Organizations
Weight = 1.0?
1
#1 opened 3 days ago
by
djuna
liked
a
model
3 days ago
liked
2
models
10 days ago
liked
a
model
11 days ago
liked
a
model
14 days ago
reacted to
leonardlin's
post with 🔥
17 days ago
Post
2171
We just released our latest Shisa V2.1 Japanese multi-lingual models: https://huggingface.co/collections/shisa-ai/shisa-v21
Besides updates to our 14B, and 70B, we have a new LFM2-based 1.2B, Llama 3.2-based 3B, and Qwen 3-based 8B, all with class-leading Japanese language capabilities.
Per usual, lots of details in the Model Cards for those interested.
Besides updates to our 14B, and 70B, we have a new LFM2-based 1.2B, Llama 3.2-based 3B, and Qwen 3-based 8B, all with class-leading Japanese language capabilities.
Per usual, lots of details in the Model Cards for those interested.
- 1 reply
upvoted
a
collection
18 days ago
liked
a
model
22 days ago
liked
a
model
23 days ago
liked
a
model
26 days ago
Diffusers library format?
1
#4 opened about 1 month ago
by
djuna
liked
a
Space
about 1 month ago
liked
a
model
about 1 month ago
reacted to
grimjim's
post with 🤗
about 1 month ago
Post
3115
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
about 1 month ago
Article
DeLERP: Decomposed Linear Interpolation for Model Merging
•
7
reacted to
grimjim's
post with 🔥
about 1 month ago
Post
5031
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
upvoted
a
paper
about 1 month ago
liked
a
model
about 2 months ago
