The Waifu Research Department

community

AI & ML interests

Waifu and Husbando Research

waifu-research-department's activity

not-lainΒ 
posted an update 5 days ago
not-lainΒ 
posted an update about 2 months ago
not-lainΒ 
posted an update about 2 months ago
view post
Post
1660
we now have more than 2000 public AI models using ModelHubMixinπŸ€—
not-lainΒ 
posted an update 2 months ago
view post
Post
4030
Published a new blogpost πŸ“–
In this blogpost I have gone through the transformers' architecture emphasizing how shapes propagate throughout each layer.
πŸ”— https://huggingface.co/blog/not-lain/tensor-dims
some interesting takeaways :
s3nhΒ 
posted an update 3 months ago
view post
Post
1992
Welcome back,

Small Language Models Enthusiasts and GPU Poor oss enjoyers lets connect.
Just created an organization which main target is to have fun with smaller models tuneable on consumer range GPUs, feel free to join and lets have some fun, much love ;3

https://huggingface.co/SmolTuners
Β·
not-lainΒ 
posted an update 4 months ago
view post
Post
2340
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 7 months ago
not-lainΒ 
posted an update 8 months ago
view post
Post
7737
I am now a huggingface fellow πŸ₯³
Β·
not-lainΒ 
posted an update 9 months ago
view post
Post
2685
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 9 months ago
view post
Post
1458
Hello beautiful people.
I wanted to thank everyone that read my blogpost and I am glad to share that we have achieved 11000 readers πŸ₯³
I couldn't have done this without you, so once again thanks a lot everyone for the support πŸ’–
If you haven't already you can read my blog post at: https://huggingface.co/blog/not-lain/rag-chatbot-using-llama3
not-lainΒ 
posted an update 10 months ago
view post
Post
2107
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 10 months ago
view post
Post
1941
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 10 months ago
view post
Post
1548
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 
posted an update 10 months ago
view post
Post
1140
I'm looking for open-source image embedding models for RAG applications and/or multimodel embedding models if they exist in the first place.

if you have any extra resources about using, creating, or finetuning them feel free to share them below πŸ€—
not-lainΒ 
posted an update 10 months ago
view post
Post
1234
πŸ₯³celebrating 5K readers in one of my blog posts πŸ₯³
I came back with another one this time πŸ€“
in this blog you will learn πŸ“– :
* How to train custom AI models with the trainer API πŸš€
* integrate your AI models with HF using the mixin classes πŸ”₯

happy reading everyone πŸ€—
πŸ”—link: https://huggingface.co/blog/not-lain/trainer-api-and-mixin-classes
  • 2 replies
Β·
not-lainΒ 
posted an update 11 months ago
not-lainΒ 
posted an update 11 months ago
view post
Post
1790
πŸš€ just reached 3K+ readers on this blog post about RAG using only HFπŸ€— related tools in just a little over 1 week from publishing.

πŸ“ƒthe most interesting thing about it is that you can use the FAISS index in the datasets library to retrieve your most similar documents.

πŸ”—https://huggingface.co/blog/not-lain/rag-chatbot-using-llama3

Happy reading everyone ✨
not-lainΒ 
posted an update 11 months ago
view post
Post
2300
πŸ”₯ **transformers** 4.40.0 is out πŸ”₯

βš™οΈ you can now push your custom pipelines easily to πŸ€—, allowing people to easily use your model in a more friendly, unified way.

πŸ€“ I already updated my blog to match the new feature https://huggingface.co/blog/not-lain/custom-architectures-with-huggingface.

πŸ“ƒA list of some repos that have custom pipelines :
* briaai/RMBG-1.4
* p1atdev/siglip-tagger-test-3
* sgugger/test-dynamic-pipeline