Hugging Face
Search models, datasets, users...
Ctrl K
Models
Datasets
Spaces
Buckets
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
39
Follow
Hari5115's profile picture
digitous's profile picture
astronomas's profile picture
107 followers
·
161 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 model
about 2 hours ago
AbstractPhil/historic-experimental-results
replied
to
their
post
about 18 hours ago
We proudly present the preview version Qwen 3.5 4b - Lucia V1.1 apache-2.0 prototype. https://huggingface.co/AbstractPhil/qwen3.5-4b-think-symbolic-image The space is set up with ZeroGPU capacity for testing. You can use Look With Help to combine a blend of prompts, or simply Free Look to test your images with just the model herself. https://huggingface.co/spaces/AbstractPhil/think-symbolic-images-testbed The first of multiple prototypes. Trained using >10,000 rows of highly complex, high quality, curated apache-friendly data, sourced as described in the recent posts and the readme. https://huggingface.co/datasets/AbstractPhil/thought-symbolic-image-recaptioned Respect the licenses. This model is not as strong as the original for museum data. In the original's case, Claude and I decided to focus on the museum information due to it being a weak-point of Qwen, sort of improve the weakness. For the new version of Lucia we couldn't use the Claude data, so the specific museum data is on the to-do list of data to curate for deep thought, not just shallow or medium thought. Really give the Lucia line some introspection capacity in the real academic sense. So the upcoming dataset improvements will improve the Lucia line substantially over time. The current model and training process preserves most of the Qwen 3.5 4b structure via very low token drift from the original model, while presenting an extractable utilizable format of multi-introspective chain of thought, formatted into a series of image captioning structures. The upcoming 4b train ready by tomorrow; is the non-commercial train with nearly 4x more rows. This non-commercial variant includes a large amount of deepfashion rows, docci rows, and coco rows. A humongous experimental model train, meant to be used for non-commercial and research purposes only. We would like to have the 9b apache variant ready by Monday and the non-commercial variant by hopefully next Friday, so the specialized forms can be trained.
published
a model
1 day ago
AbstractPhil/historic-experimental-results
View all activity
Organizations
AbstractPhil
's datasets
91
Sort: Recently updated
AbstractPhil/thought-symbolic-image-recaptioned
Viewer
•
Updated
5 days ago
•
40.5k
•
134
AbstractPhil/ffhq-recaptioned
Viewer
•
Updated
12 days ago
•
70k
•
83
AbstractPhil/deepfashion-multimodal-recaptioned
Viewer
•
Updated
12 days ago
•
42.5k
•
242
AbstractPhil/qwen-thinking-images
Viewer
•
Updated
12 days ago
•
444k
•
3.73k
AbstractPhil/thought-symbolic-image-captions
Viewer
•
Updated
17 days ago
•
1.12M
•
822
AbstractPhil/geolip-beatrix-anima-data
Viewer
•
Updated
28 days ago
•
5.1k
•
2.94k
AbstractPhil/mega-liminal
Viewer
•
Updated
Sep 26
•
1.87k
•
550
AbstractPhil/beatrix-captured-interactive-inferences
Updated
Sep 23
•
83
AbstractPhil/alephllm-chat-history
Viewer
•
Updated
Aug 15
•
1
•
38
AbstractPhil/captionbert-8192-v2-consensus
Updated
Aug 1
•
1.7k
AbstractPhil/conceptual-captions-12m-webdataset-berts
Viewer
•
Updated
Aug 1
•
32.3M
•
14.9k
•
1
AbstractPhil/bulk-cc12m-features
Viewer
•
Updated
Jul 31
•
121M
•
1.74k
AbstractPhil/tower-probes-results
Viewer
•
Updated
Jul 22
•
17
•
56
AbstractPhil/qwen-deepfashion-fused
Viewer
•
Updated
Jul 12
•
122k
•
768
•
1
AbstractPhil/qwen-synth-characters-fused
Viewer
•
Updated
Jul 10
•
42.7k
•
1.2k
AbstractPhil/qwen-synth-characters-100-json-test
Viewer
•
Updated
Jul 10
•
1k
•
41
AbstractPhil/anima-brent-90k-cache
Updated
Jul 5
•
87
AbstractPhil/qwen-synth-characters
Viewer
•
Updated
Jul 3
•
61k
•
1.21k
AbstractPhil/qwen-deepfashion
Viewer
•
Updated
Jul 3
•
160k
•
1.61k
AbstractPhil/diffusion-pipe-cache-test1
Viewer
•
Updated
Jun 27
•
8.92k
•
19
AbstractPhil/anima-90k-cache
Updated
Jun 26
•
261
AbstractPhil/diffusion-pretrain-set-ft1
Viewer
•
Updated
Jun 23
•
1.46M
•
2.68k
•
2
AbstractPhil/diffusion-pretrain-set-ft1-1024
Viewer
•
Updated
Jun 11
•
1.14M
•
760
AbstractPhil/sdxl-qwen-phase1-cache
Viewer
•
Updated
Jun 6
•
86k
•
271
AbstractPhil/geolip-sdxl-fid-scoring
Viewer
•
Updated
Jun 5
•
2.8k
•
113
AbstractPhil/sdxl-qwen-phase0
Viewer
•
Updated
Jun 4
•
86k
•
596
•
3
AbstractPhil/IMDB-PUBLIC-SCRAPED
Preview
•
Updated
May 19
•
556
•
1
AbstractPhil/ldhnam-deepfashion_controlnet
Viewer
•
Updated
May 19
•
26k
•
30
AbstractPhil/ffhq_flux_latents_repaired
Viewer
•
Updated
May 19
•
40.8k
•
236
AbstractPhil/synthetic-characters
Viewer
•
Updated
May 19
•
149k
•
122
Previous
1
2
3
4
Next