RecursiveSI/flint
Text Generation • 40B • Updated • 420 • 545
Patrick Devaney
patrickbdevaney
AI & ML interests
mamba s4, mixtral 8x-7b, candle, pytorch
Recent Activity
liked a model about 6 hours ago
RecursiveSI/flint liked a model about 6 hours ago
InternScience/Sage-A1.5 liked a model 3 days ago
gordonhu/Tev-320BOrganizations
liked 2
models about 6 hours ago
liked 6
models 3 days ago
gordonhu/Tev-320B
Text Generation • 321B • Updated • 382 • 12
respanai/span-02
Image-Text-to-Text • 16B • Updated • 388 • 26
amazon/ALoDLM-8B
Text Generation • 8B • Updated • 1.83k • 62
sabicap/sabi-noema
Text Generation • 27B • Updated • 947 • 33
nvidia/Nemotron-3.5-Parse
Image-Text-to-Text • 0.6B • Updated • 1.8k • 77
nvidia/NV-Reason-CT
Image-Text-to-Text • 5B • Updated • 7.07k • 81
liked a
model 5 days ago
updated 3
models 11 days ago
reacted to pollix's post with ❤️ 22 days ago
Post
6,455
stuntd 0.1.2 is out 🎉
stuntd sits in front of your LLM, learns its typed decisions and answers the confident ones locally with a small head on the Laya encoder by @convaiinnovations . About 20ms on GPU and 60ms on CPU, and anything it isn't sure about still goes to the big model.
New in 0.1.2:
- decisions with several fields, like category + urgency + needs_human in one call, answered locally only when every field is sure
- the Anthropic Messages API learns too, not only OpenAI
- auto_retrain: the daemon retrains a site in the background once enough new traffic comes in, so collect, train, shadow and live run on their own
- serve --lazy loads the checkpoint on the first request
Try it in the browser: pollix/stuntd
Code: https://github.com/bladedevoff/stuntd
stuntd sits in front of your LLM, learns its typed decisions and answers the confident ones locally with a small head on the Laya encoder by @convaiinnovations . About 20ms on GPU and 60ms on CPU, and anything it isn't sure about still goes to the big model.
New in 0.1.2:
- decisions with several fields, like category + urgency + needs_human in one call, answered locally only when every field is sure
- the Anthropic Messages API learns too, not only OpenAI
- auto_retrain: the daemon retrains a site in the background once enough new traffic comes in, so collect, train, shadow and live run on their own
- serve --lazy loads the checkpoint on the first request
Try it in the browser: pollix/stuntd
Code: https://github.com/bladedevoff/stuntd
pip install -U stuntd
- 1 reply
updated a
model 22 days ago
updated a
model 26 days ago
Broken model unfortunately
3
#1 opened 26 days ago
by 
iamtanmay
liked a
dataset 27 days ago
published 2
models 27 days ago
liked a
model about 1 month ago
