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
26
Follow
John6666's profile picture
Dapdek26's profile picture
webxos's profile picture
92 followers
·
126 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
updated
a dataset
about 5 hours ago
AbstractPhil/bulk-cc12m-features
updated
a collection
about 19 hours ago
GeoLIP
posted
an
update
1 day ago
https://huggingface.co/AbstractPhil/clip-vitb-mini-distilled The semi-successful run series on the VIT-B lineup is live and full of useful baseline distillation information for feature + InfoNCE distillation processing as well as direct feature distillation processing, direct InfoNCE distillation, and multiple other tested methods. https://huggingface.co/blog/AbstractPhil/geometric-memory-ft4 This article showcases the baseline utilization and benchmarks of the earlier experiment line's objective and loss structures tested on 12m features for the vit-b baseline. Not the strongest showcase, but the strongest of the champions did show some serious promise. Next setup will be a directly aligned set based on the loss and objectives decided by the champions in the first runs, for the second run they operate in direct conjunction with the bert-8192 and captionbert-8192 distillation format directly on clip-vit-l features - this time we're including DINOv3 into the mix for it's high potency. I'm currently extracting 4 clip-vit-l variants for the CC12m features and will be running the next series on the L size, which will give considerably more active and useful features overall within a smaller package. The captionbert-8192 has a more unique and difficult to tune for pixel processing parity, but I will spend a few days making sure the smaller prototypes fit before I run the large experiments in order to build towards the larger objectives. Primarily I need to ensure the memory bank aligns correctly and the constellation conforms to the anchors correctly, as this process was not micro managed enough for this run. The results are nonetheless useful and potent. The process continues until we cover the entire constellation series.
View all activity
Organizations
AbstractPhil
's datasets
81
Sort: Recently updated
AbstractPhil/bulk-cc12m-features
Viewer
•
Updated
3 minutes ago
•
21.9M
•
42
AbstractPhil/tower-probes-results
Viewer
•
Updated
9 days ago
•
17
•
87
AbstractPhil/qwen-deepfashion-fused
Viewer
•
Updated
19 days ago
•
122k
•
2.92k
•
1
AbstractPhil/qwen-synth-characters-fused
Viewer
•
Updated
21 days ago
•
42.7k
•
2.2k
AbstractPhil/qwen-synth-characters-100-json-test
Viewer
•
Updated
21 days ago
•
1k
•
79
AbstractPhil/anima-brent-90k-cache
Updated
26 days ago
•
546
AbstractPhil/qwen-synth-characters
Viewer
•
Updated
28 days ago
•
61k
•
747
AbstractPhil/qwen-deepfashion
Viewer
•
Updated
28 days ago
•
160k
•
1.59k
AbstractPhil/diffusion-pipe-cache-test1
Viewer
•
Updated
Jun 27
•
8.92k
•
82
AbstractPhil/anima-90k-cache
Updated
Jun 26
•
108
AbstractPhil/diffusion-pretrain-set-ft1
Viewer
•
Updated
Jun 23
•
1.46M
•
1.23k
•
1
AbstractPhil/diffusion-pretrain-set-ft1-1024
Viewer
•
Updated
Jun 11
•
1.14M
•
708
AbstractPhil/sdxl-qwen-phase1-cache
Viewer
•
Updated
Jun 6
•
86k
•
202
AbstractPhil/geolip-sdxl-fid-scoring
Viewer
•
Updated
Jun 5
•
2.8k
•
92
AbstractPhil/sdxl-qwen-phase0
Viewer
•
Updated
Jun 4
•
86k
•
135
•
3
AbstractPhil/IMDB-PUBLIC-SCRAPED
Preview
•
Updated
May 19
•
53
•
1
AbstractPhil/ldhnam-deepfashion_controlnet
Viewer
•
Updated
May 19
•
26k
•
25
AbstractPhil/ffhq_flux_latents_repaired
Viewer
•
Updated
May 19
•
40.8k
•
161
AbstractPhil/synthetic-characters
Viewer
•
Updated
May 19
•
149k
•
128
AbstractPhil/CN_pose3D_V10_512
Viewer
•
Updated
May 19
•
66.5k
•
37
AbstractPhil/CN_pose3D_V7_512
Viewer
•
Updated
May 19
•
255k
•
730
AbstractPhil/synthetic-object-relations-json
Viewer
•
Updated
May 18
•
5k
•
39
AbstractPhil/cc-task1-json
Preview
•
Updated
May 18
•
30
AbstractPhil/cc-prompts-sharded
Viewer
•
Updated
May 15
•
3.32M
•
4
AbstractPhil/json-coco-format
Viewer
•
Updated
May 14
•
129k
•
165
AbstractPhil/svae-freckles-4096-cifar10
Viewer
•
Updated
Apr 10
•
60k
•
50
AbstractPhil/ryan-spearman-prepared-features
Viewer
•
Updated
Mar 27
•
1
•
4
AbstractPhil/conceptual-captions-12m-webdataset-berts
Viewer
•
Updated
Mar 20
•
32.3M
•
494
•
1
AbstractPhil/bertenstein-v1
Viewer
•
Updated
Mar 7
•
37.4k
•
700
AbstractPhil/residual-thinking-embeddings
Updated
Mar 3
•
58
Previous
1
2
3
Next