Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Hardware
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
🤝
Open to Collab
358.3
TFLOPS
AbstractPhila
PRO
AbstractPhil
19
6
30
P(doom)
Rejects the premise
Follow
xziayro's profile picture
Ujjwal-Tyagi's profile picture
tegridydev's profile picture
107 followers
·
148 following
https://civitai.com/user/AbstractPhila
AbstractEyes
AI & ML interests
datasets, research papers, experimentation, vision, classification, text encoders, tokenization, llms, diffusion, distillation, and more.
Recent Activity
posted
an
update
3 minutes ago
Mini-Beatrix-V2-control-softmax is complete. The model is substantially more intelligent than the counterparts. https://huggingface.co/AbstractPhil/alephllm-mini-beatrix-training/tree/main/mini-beatrix-2s-control-attn-fp16-r10k --- With that information I have built the tests required to create a smaller and substantially more powerful variant. Nano-Beatrix-V4 will have hundreds of trains as intelligent as the V3 version within a few days. I will be slowly pushing up the capacity as each will train a hundred thousand steps within a couple hours on a colab card. Roughly 400k byte/s or so, these shallow models have nearly perfect recon at 4096 context length. HOWEVER, a full matching corpus train that fed Beatrix V3 60 billion bytes - is only about 2 days or less on a colab card vs the near 20 for the v3. RECON won't guarantee intelligence, however these tiny models here will train so quickly that I can directly test which is eating what space and why, then increase that with minimal cost through direct minimal expansion and then genetic interpolation, until the model hits around 200k token/s or so. Essentially these lightning quick little models will be capable of attaching to other models, training miniature modular routing systems with the quiet loss structure attached to other models. They won't control a big model, but that's what the mini version is for.
updated
a model
44 minutes ago
AbstractPhil/alephllm-mini-beatrix-training
updated
a bucket
about 2 hours ago
AbstractPhil/alephllm-chat-storage
View all activity
Organizations
AbstractPhil
's models
223
Sort: Recently updated
AbstractPhil/geoclip-vit-base-patch-32-1024d
Updated
Aug 28, 2025
AbstractPhil/geoclip-vit-base-patch-32-512d
Updated
Aug 28, 2025
AbstractPhil/geometric-diffusion-cifar100-p2048
Updated
Aug 26, 2025
AbstractPhil/geometric-diffusion-cifar100
Updated
Aug 25, 2025
AbstractPhil/beeper-ascii-v1
Text Generation
•
Updated
Aug 25, 2025
AbstractPhil/beeper-rose-v4
Text Generation
•
Updated
Aug 25, 2025
•
23
AbstractPhil/beeper-rose-v3
Updated
Aug 17, 2025
•
15
AbstractPhil/beeper-rose-v2
Updated
Aug 17, 2025
•
14
AbstractPhil/beeper-rose-tinystories-6l-512d-ctx512
Updated
Aug 17, 2025
•
108
AbstractPhil/beeper-tinystories-6l-512d-ctx512
Updated
Aug 17, 2025
•
108
AbstractPhil/tiny-gpt-tests
27.6M
•
Updated
Aug 17, 2025
•
13
AbstractPhil/pentachora-greyscale-frequency-encoded
Zero-Shot Classification
•
Updated
Aug 17, 2025
AbstractPhil/experimental_pentachora
Updated
Aug 17, 2025
AbstractPhil/mirel-gpt-oss-20b
Updated
Aug 9, 2025
AbstractPhil/bert-beatrix-2048
0.1B
•
Updated
Jul 14, 2025
•
23
•
1
AbstractPhil/bert-beatrix-2048-noobxl-epsilon-v11-dual-shunt-adapter_clip_g
Updated
Jun 25, 2025
AbstractPhil/bert-beatrix-2048-noobxl-epsilon-v11-dual-shunt-adapter
Updated
Jun 25, 2025
AbstractPhil/bert-beatrix-2048-vit-bigG-14-dual-shunt-adapter
Updated
Jun 21, 2025
AbstractPhil/bert-beatrix-2048-vit-l-14-dual-shunt-adapter
Updated
Jun 19, 2025
AbstractPhil/resonance-model-zoo
Updated
Jun 10, 2025
AbstractPhil/t5-flan-base-vit-l-14-dual-stream-adapter
Updated
Jun 6, 2025
•
19
•
3
AbstractPhil/t5-flan-base-vit-bigG-14-dual-stream-adapter
Updated
May 31, 2025
•
26
•
3
AbstractPhil/t5-vit-14-v1
Any-to-Any
•
Updated
May 23, 2025
•
2
AbstractPhil/robust-velocity-adapter
Updated
May 21, 2025
•
1
AbstractPhil/T5-Small-Human-Attentive-Try2-Pass3
60.5M
•
Updated
May 20, 2025
•
18
AbstractPhil/T5-Small-Human-Attentive-Try2-Pass2
60.5M
•
Updated
May 19, 2025
•
13
AbstractPhil/T5-Small-Human-Attentive-Try2
60.5M
•
Updated
May 19, 2025
•
12
AbstractPhil/T5-Small-Human-Attentive
60.5M
•
Updated
May 18, 2025
•
13
AbstractPhil/SD15-Surge-V1
0.9B
•
Updated
May 3, 2025
•
2
AbstractPhil/Liminal-Full
Updated
Apr 22, 2025
•
3
Previous
1
...
5
6
7
8
Next