AI & ML interests

AI in the Arabic field

Recent Activity

tunis-ai's activity

not-lainΒ 
posted an update 3 months ago
BilsΒ 
posted an update 3 months ago
view post
Post
4973
Spatial sound experience! SonicOrbit features AI beat detection to auto-sync your rhythm.

Bils/SonicOrbit
not-lainΒ 
in tunis-ai/TunBERT 3 months ago

Labels

1
#5 opened 3 months ago by
kmailiaymen10

fix pipeline

6
#4 opened over 1 year ago by
not-lain
BilsΒ 
posted an update 3 months ago
view post
Post
2161
create amazing audio ads in just a few steps
Bils/AIPromoStudio
not-lainΒ 
posted an update 4 months ago
BilsΒ 
posted an update 4 months ago
view post
Post
2118
πŸš€ We're excited to share major improvements to our Janus-Pro-7B Text-to-Image Generation Space!
🎨What's New:
1-Critical Bug Fixes
2-Enhanced Features
3-UI Improvements
4-Performance Boost
Try It Now:
Bils/DeepseekJanusPro-Image
BilsΒ 
posted an update 4 months ago
view post
Post
1886
πŸš€ Explore the powerful Janus-Pro-7B Text-to-Image Generator! Transform your prompts into stunning visuals with state-of-the-art AI.
Bils/DeepseekJanusPro-Image
  • 2 replies
Β·
not-lainΒ 
posted an update 5 months ago
view post
Post
1765
we now have more than 2000 public AI models using ModelHubMixinπŸ€—
not-lainΒ 
posted an update 5 months ago
not-lainΒ 
posted an update 7 months ago
view post
Post
2408
ever wondered how you can make an API call to a visual-question-answering model without sending an image url πŸ‘€

you can do that by converting your local image to base64 and sending it to the API.

recently I made some changes to my library "loadimg" that allows you to make converting images to base64 a breeze.
πŸ”— https://github.com/not-lain/loadimg

API request example πŸ› οΈ:
from loadimg import load_img
from huggingface_hub import InferenceClient

# or load a local image
my_b64_img = load_img(imgPath_url_pillow_or_numpy ,output_type="base64" ) 

client = InferenceClient(api_key="hf_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx")

messages = [
	{
		"role": "user",
		"content": [
			{
				"type": "text",
				"text": "Describe this image in one sentence."
			},
			{
				"type": "image_url",
				"image_url": {
					"url": my_b64_img # base64 allows using images without uploading them to the web
				}
			}
		]
	}
]

stream = client.chat.completions.create(
    model="meta-llama/Llama-3.2-11B-Vision-Instruct", 
	messages=messages, 
	max_tokens=500,
	stream=True
)

for chunk in stream:
    print(chunk.choices[0].delta.content, end="")
not-lainΒ 
posted an update 10 months ago
not-lainΒ 
posted an update 11 months ago
view post
Post
7796
I am now a huggingface fellow πŸ₯³
Β·
not-lainΒ 
posted an update 11 months ago
view post
Post
2709
I have finished writing a blogpost about building an image-based retrieval system, This is one of the first-ever approaches to building such a pipeline using only open-source models/libraries πŸ€—

You can checkout the blogpost in https://huggingface.co/blog/not-lain/image-retriever and the associated space at not-lain/image-retriever .

✨ If you want to request another blog post consider letting me know down below or you can reach out to me through any of my social media

πŸ“– Happy reading !
not-lainΒ 
posted an update 12 months ago
not-lainΒ 
posted an update about 1 year ago
view post
Post
2133
It is with great pleasure I inform you that huggingface's ModelHubMixin reached 200+ models on the hub πŸ₯³

ModelHubMixin is a class developed by HF to integrate AI models with the hub with ease and it comes with 3 methods :
* save_pretrained
* from_pretrained
* push_to_hub

Shoutout to @nielsr , @Wauplin and everyone else on HF for their awesome work πŸ€—

If you are not familiar with ModelHubMixin and you are looking for extra resources you might consider :
* docs: https://huggingface.co/docs/huggingface_hub/main/en/package_reference/mixins
πŸ”—blog about training models with the trainer API and using ModelHubMixin: https://huggingface.co/blog/not-lain/trainer-api-and-mixin-classes
πŸ”—GitHub repo with pip integration: https://github.com/not-lain/PyTorchModelHubMixin-template
πŸ”—basic guide: https://huggingface.co/posts/not-lain/884273241241808
not-lainΒ 
posted an update about 1 year ago
view post
Post
1957
I will be delivering an introductory coding session this Sunday 7Pm gmt+1 time about huggingface, if you are new to HF and don't know where to begin, you are welcome to join us πŸ€—
πŸ“ŒPlace: huggingface discord server
πŸ”—Link : https://discord.gg/hugging-face-879548962464493619?event=1245406127668203541
  • 2 replies
Β·
not-lainΒ 
posted an update about 1 year ago
view post
Post
1560
If you're a researcher or developing your own model πŸ‘€ you might need to take a look at huggingface's ModelHubMixin classes.
They are used to seamlessly integrate your AI model with huggingface and to save/ load your model easily πŸš€

1️⃣ make sure you're using the appropriate library version
pip install -qU "huggingface_hub>=0.22"

2️⃣ inherit from the appropriate class
from huggingface_hub import PyTorchModelHubMixin
from torch import nn

class MyModel(nn.Module,PyTorchModelHubMixin):
  def __init__(self, a, b):
    super().__init__()
    self.layer = nn.Linear(a,b)
  def forward(self,inputs):
    return self.layer(inputs)

first_model = MyModel(3,1)

4️⃣ push the model to the hub (or use save_pretrained method to save locally)
first_model.push_to_hub("not-lain/test")

5️⃣ Load and initialize the model from the hub using the original class
pretrained_model = MyModel.from_pretrained("not-lain/test")

not-lainΒ 
updated a Space about 1 year ago