Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Log In
Sign Up
In a Training Loop 🔄
16.2
TFLOPS
568
2421
30368
John Smith
PRO
John6666
Follow
p3nGu1nZz's profile picture
Supertimor46's profile picture
macgaga's profile picture
1,737 followers
·
3,803 following
John6666cat
AI & ML interests
None yet
Recent Activity
reacted
to
mrs83
's
post
with 👀
about 5 hours ago
While the https://huggingface.co/flwrlabs community gathered in London for their Summit, we released https://huggingface.co/ethicalabs/FlowerTune-Echo-DSRN-114M-Finance-PEFT onto the Flower Hub: a federated PEFT adapter for financial sentiment, built on a novel architecture called Echo-DSRN, a project I started working on 2 years ago. The core problem we set out to solve: financial data on ledgers, earnings calls, tick streams, blows up the memory footprint of standard Transformers. KV-Cache scaling makes federated training on the edge increasingly difficult. You cannot preserve data privacy if your decentralized nodes keep running out of memory. Echo-DSRN addresses this at the architectural level. It uses a dual recurrent state design: a GRU fast path for short-range dynamics, and a surprise-gated slow memory whose write intensity is modulated by prediction error. The result is O(1) memory regardless of context length. Runs on CPU, AMD ROCm, Apple MPS, NVIDIA GPUs. Combined with the Flower federated framework, financial institutions can now run local fine-tuning on proprietary data without it ever leaving their infrastructure. Results on standard financial sentiment benchmarks: → FPB: 70.2% → TFNS: 70.2% → FIQA: 63.8% This is a 114M baseline. The next step is scaling. The surprise gating mechanism independently converged on what https://huggingface.co/google described in their Titans paper. No working open implementation existed. This one does. Flower Hub: https://flower.ai/apps/mrs83/echo-dsrn-114m-finance Hugging Face: https://huggingface.co/ethicalabs/FlowerTune-Echo-DSRN-114M-Finance-PEFT
updated
a collection
about 5 hours ago
Resources for Sound Processing
liked
a model
about 5 hours ago
yuriyvnv/parakeet-tdt-0.6b-polish
View all activity
Organizations
John6666
's datasets
55
Sort: Recently updated
John6666/knowledge_base_md_for_rag_1
Updated
1 day ago
•
24.8k
•
5
John6666/forum3
Updated
6 days ago
•
10.1k
•
15
John6666/sdxl-backup-202502
Updated
Feb 12
•
17
John6666/sdxl-backup-202412
Updated
Feb 12
•
244
•
1
John6666/model-mirror-8
Updated
Feb 12
•
55
John6666/model-mirror-9
Updated
Feb 12
•
253
John6666/model-mirror-7
Updated
Feb 12
•
113
John6666/model-mirror-4
Updated
Feb 12
•
244
John6666/model-mirror-5
Updated
Feb 12
•
93
John6666/model-mirror-6
Updated
Feb 12
•
128
John6666/model-mirror-3
Updated
Feb 12
•
88
John6666/model-mirror-29
Updated
Feb 12
•
432
John6666/model-mirror-27
Updated
Feb 12
•
110
John6666/model-mirror-28
Updated
Feb 12
•
172
John6666/model-mirror-26
Updated
Feb 12
•
240
•
1
John6666/model-mirror-25
Updated
Feb 12
•
137
John6666/model-mirror-23
Updated
Feb 12
•
154
John6666/model-mirror-24
Updated
Feb 12
•
71
John6666/model-mirror-22
Updated
Feb 12
•
157
•
1
John6666/model-mirror-21
Updated
Feb 12
•
124
•
1
John6666/model-mirror-2
Updated
Feb 12
•
142
John6666/model-mirror-20
Updated
Feb 12
•
36
John6666/model-mirror-19
Updated
Feb 12
•
78
John6666/model-mirror-18
Updated
Feb 12
•
121
John6666/model-mirror-16
Updated
Feb 12
•
321
•
1
John6666/model-mirror-17
Updated
Feb 12
•
301
John6666/model-mirror-15
Updated
Feb 12
•
282
John6666/model-mirror-13
Updated
Feb 12
•
155
John6666/model-mirror-14
Updated
Feb 12
•
163
John6666/model-mirror-11
Updated
Feb 12
•
157
Previous
1
2
Next