black-forest-labs/FLUX.1-schnell
Text-to-Image
•
Updated
•
870k
•
•
3.1k
Tom Hunn
thunnai
AI & ML interests
I've been working in generative AI since it was still called "Deep Learning." Most of my experience is in the audio space, but I've also worked on projects involving llms.
I've had hands-on experience across the full AI product lifecycle, including:
- AI Research & Model Training
- MLOps & Productionizing Models
- Product Strategy — exploring what’s possible with emerging tech
Recent Activity
liked
a model
7 days ago
black-forest-labs/FLUX.1-schnell
liked
a model
9 days ago
FrancisRing/StableAnimator
liked
a model
9 days ago
franciszzj/Leffa
Organizations
None yet
thunnai's activity
liked
a
model
7 days ago
liked
4
models
9 days ago
reacted to
MoritzLaurer's
post with 🔥
13 days ago
Post
1264
I've been building a small library for working with prompt templates on the HF hub:
The community currently shares prompt templates in a wide variety of formats: in datasets, in model cards, as strings in .py files, as .txt/.yaml/.json/.jinja2 files etc. This makes sharing and working with prompt templates unnecessarily complicated.
Prompt templates are currently the main hyperparameter that people tune when building complex LLM systems or agents. If we don't have a common standard for sharing them, we cannot systematically test and improve our systems. After comparing different community approaches, I think that working with modular .yaml or .json files is the best approach.
The
- proposes a standard for sharing prompts (entirely locally or on the HF hub)
- provides some utilities that are interoperable with the broader ecosystem
Try it:
The library is in early stages, feedback is welcome!
More details in the docs: https://github.com/MoritzLaurer/prompt_templates/
pip install prompt-templates. Motivation: The community currently shares prompt templates in a wide variety of formats: in datasets, in model cards, as strings in .py files, as .txt/.yaml/.json/.jinja2 files etc. This makes sharing and working with prompt templates unnecessarily complicated.
Prompt templates are currently the main hyperparameter that people tune when building complex LLM systems or agents. If we don't have a common standard for sharing them, we cannot systematically test and improve our systems. After comparing different community approaches, I think that working with modular .yaml or .json files is the best approach.
The
prompt-templates library : - proposes a standard for sharing prompts (entirely locally or on the HF hub)
- provides some utilities that are interoperable with the broader ecosystem
Try it:
# !pip install prompt-templates
from prompt_templates import PromptTemplateLoader
prompt_template = PromptTemplateLoader.from_hub(repo_id="MoritzLaurer/closed_system_prompts", filename="claude-3-5-artifacts-leak-210624.yaml")The library is in early stages, feedback is welcome!
More details in the docs: https://github.com/MoritzLaurer/prompt_templates/
- 1 reply
replied to
freddyaboulton's
post
14 days ago
Awesome work on this! Another big win for rapid prototyping with Gradio!
reacted to
freddyaboulton's
post with 🚀🔥
14 days ago
Post
1050
Just created a cookbook of real time audio/video spaces created using Gradio and WebRTC ⚡️
Use this and the [docs](https://freddyaboulton.github.io/gradio-webrtc/) to get started building the next gen of AI apps!
freddyaboulton/gradio-webrtc-cookbook-6758ba7745aeca7b1be7de0f
Use this and the [docs](https://freddyaboulton.github.io/gradio-webrtc/) to get started building the next gen of AI apps!
freddyaboulton/gradio-webrtc-cookbook-6758ba7745aeca7b1be7de0f
-
- 2 replies
liked
a
Space
16 days ago
liked
a
model
16 days ago
liked
a
model
20 days ago
liked
a
Space
20 days ago
liked
a
model
22 days ago
liked
2
models
24 days ago
liked
a
model
28 days ago
liked
a
model
about 1 month ago
liked
a
dataset
about 1 month ago
reacted to
TuringsSolutions's
post with 👀
about 1 month ago
Post
861
I created something called 'Hyperbolic Embeddings'. I literally just embed the tokens into Hyperbolic Space instead of Euclidean space. At first, this did not get me the gains I was expecting. I was a sad panda. Then I thought about it, a Hyperbolic Embedding needs a Hyperbolic Optimizer. So, instead of Adam, I used Riemannian Adam (RAdam). "Ladies and Gentlemen, We Got 'Em!"
- 28 replies