Hugging Face's logo
Activity Feed Request to join this org

AI & ML interests

None defined yet.
vilarinΒ 
posted an update over 1 year ago
view post
Post
1951
A few days ago, Blackforestlabs released FLUX.1 Tools, which has surprised everyone with its quality and effects. Now that diffusers support these features, you can easily deploy and build your own Tools.
Combined with the powerful Gradio and ZeroGPU, you can experience the Tools immediately, which is truly wonderful.
I was impressed by the Flux.1 Fill dev, so here I've built a demo for it, making it easy to use for inpainting and outpainting images.

πŸ„Model: black-forest-labs/FLUX.1-Fill-dev
πŸ¦–Demo: vilarin/Flux.1-Fill-dev
πŸ‘diffusers: https://github.com/huggingface/diffusers/tree/main/src/diffusers/pipelines/flux
vilarinΒ 
posted an update over 1 year ago
view post
Post
1650
πŸ„β€β™‚οΈWhile browsing new models, I stumbled upon Lumiere from aixonlab. After testing it, I feel it has considerable potential. Keep up the good work!

Lumiere Alpha is a model focusing on improving realism without compromising prompt coherency or changing the composition completely from the original Flux.1-Dev model.

πŸ¦„ Model: aixonlab/flux.1-lumiere-alpha

πŸ¦– Demo: vilarin/lumiere
  • 2 replies
Β·
vilarinΒ 
posted an update almost 2 years ago
vilarinΒ 
posted an update almost 2 years ago
view post
Post
6134
🀩 Amazing day. AWPortrait-FL finally here!
πŸ¦– AWPortrait-FL is finetuned on FLUX.1-dev using the training set of AWPortrait-XL and nearly 2,000 fashion photography photos with extremely high aesthetic quality.

πŸ€—Model: Shakker-Labs/AWPortrait-FL

πŸ™‡Demo: vilarin/flux-labs

  • 6 replies
Β·
vilarinΒ 
posted an update almost 2 years ago
vilarinΒ 
posted an update almost 2 years ago
view post
Post
4277
Black Forest Labs, BASED! πŸ‘
FLUX.1 is more delightful, with good instruction following.
FLUX.1 dev( black-forest-labs/FLUX.1-dev) with a 12B parameter distillation model, second only to Black Forest Labs' state-of-the-art model FLUX.1 pro. πŸ™€

Update πŸ€™Official demo:
black-forest-labs/FLUX.1-dev
  • 2 replies
Β·
TonicΒ 
posted an update almost 2 years ago
view post
Post
1728
πŸ™‹πŸ»β€β™‚οΈ Hey there folks

made a demo for Nvidia Minitron on an A100.

Minitron is a family of small language models (SLMs) obtained by pruning NVIDIA's Nemotron-4 15B model. We prune model embedding size, attention heads, and MLP intermediate dimension, following which, we perform continued training with distillation to arrive at the final models.

Deriving the Minitron 8B and 4B models from the base 15B model using our approach requires up to 40x fewer training tokens per model compared to training from scratch; this results in compute cost savings of 1.8x for training the full model family (15B, 8B, and 4B). Minitron models exhibit up to a 16% improvement in MMLU scores compared to training from scratch, perform comparably to other community models such as Mistral 7B, Gemma 7B and Llama-3 8B, and outperform state-of-the-art compression techniques from the literature. Please refer to our arXiv paper for more details.

Minitron models are for research and development only.

source : nvidia/Minitron-8B-Base
demo : Tonic/Minitron
  • 1 reply
Β·
TonicΒ 
posted an update about 2 years ago
view post
Post
1646
No on really pays attention to voyage ai , but probably you should πŸ˜‰
voyageai
  • 4 replies
Β·
TonicΒ 
posted an update about 2 years ago
view post
Post
2562
appreciation post for @osanseviero + huggingface staff (@reach-vb , @merve , many others many many others) , that fight hard for many weeks / months to fix the releases in many organisations to make it easier for us to test out so many things ... πŸ€—πŸ€—πŸ€— thanks for that folks !
  • 1 reply
Β·
TonicΒ 
posted an update about 2 years ago
view post
Post
1953
my πŸ€—huggingface activity for 2024 so far ...

dont tell my boss...

check yours too now, it's fun πŸ€—
  • 3 replies
Β·
TonicΒ 
posted an update about 2 years ago
view post
Post
867
all these GPU bourgeois tryna act cool like the GPU poor kids...
- what's your number for real ?
+ and did it work at parties for you ?
TonicΒ 
posted an update about 2 years ago
TonicΒ 
posted an update about 2 years ago
view post
Post
1253
πŸ™‹πŸ»β€β™‚οΈhey there folks !

i got an email my space was down so now my space is back up ! StarCoder2 (Raw) on A100 , for your enjoyment and apache2 research purposes πŸ‘πŸ»πŸ‘πŸ»

Tonic/starcoder2

check my profile for more cool GPUzero demos, i'll cycle them with some new overlooked models soon πŸ’–πŸ€—
TonicΒ 
posted an update over 2 years ago
view post
Post
there were only 5 Major Releases last week !

😱 it's so over
  • 1 reply
Β·
TonicΒ 
posted an update over 2 years ago
view post
Post
LAST CHANCE TO TRY 🌟STARCODER2

After today it's gone !

actually not - just joking ! it's <3 open source !

just trying to get folks' attention to my featured "Spaces of the Week" :

Tonic/starcoder2

drop a like for your boy and join us next week for making fine tunes !
TonicΒ 
posted an update over 2 years ago
view post
Post
Last day on Spaces of the Week ,
and we made it to last place on trending.
i really thought it couldnt get any better, but i'm crying ! 😭

The thing i like the most about ZeroGPU , import spaces , is that i dont have to always check to see if someone decided to test if i have hard character limits , and it reloads the application flawlessly .

drop a like on my spaces here :
Spaces of the Week : https://huggingface.co/spaces/tonic/starcoder2
9 other ZeroGPU demos : tonic
TonicΒ 
posted an update over 2 years ago
view post
Post
hey there folks new Yi model just came out , and i had a gradio interface ready since their last releases.

it's just a base model but you can check it out here : Tonic/Yi-9B

cant wait to fine tune this one πŸ€—πŸš€
TonicΒ 
posted an update over 2 years ago
view post
Post
πŸ™‹πŸ»β€β™‚οΈ hey there folks ,

Star coder came out and it's really fascinating in more ways than one !

first off it codes well already. but secondly it's reported to "know" 101 programming languages !

that actually means it's ripe for fine tunes, so if you're like me you've been bookmarking cool datasets and cant wait to get started !

that said , here's a cool demo where you can try it out now : Tonic/starcoder2

turns out it can program a T5 demo using gradio !
TonicΒ 
posted an update over 2 years ago
view post
Post
πŸ™‹πŸ»β€β™‚οΈhey there folks ,

πŸ€—Aya has been released ! It's an absolutely massive undertaking to create a huge multilingual dataset and multilingual model of very high quality.

Papers :
https://cohere.com/research/papers/aya-dataset-paper-2024-02-13
https://cohere.com/research/papers/aya-model-paper-2024-02-13

Model : https://huggingface.co/CohereForAI/aya-101
Dataset : https://huggingface.co/datasets/CohereForAI/aya_dataset


I am proud to be one of 3,000 humans who built Aya - a new massively multilingual, generative LLM that outperforms existing open-source models and covers 101 different languages. Together, we are accelerating multilingual AI. πŸ€—
  • 1 reply
Β·
TonicΒ 
posted an update over 2 years ago