Hafedh Hichri

not-lain

AI & ML interests

custom AI models with HF integration, multimodal rag and open-source contributions && may or may not be a huggingface fellow

Recent Activity

Articles

Organizations

Stanford AI's profile picture AI FILMS's profile picture MusicAI's profile picture BigScience Biomedical Datasets's profile picture OpenVINO Toolkit's profile picture Hugging Face Fellows's profile picture Gradio-Blocks-Party's profile picture scikit-learn's profile picture DeepGHS's profile picture Open-Source AI Meetup's profile picture AMD's profile picture lora concepts library's profile picture The introspector project's profile picture Arabic Machine Learning 's profile picture Literally Me FRFR Research Society's profile picture East China Normal University's profile picture Kornia AI's profile picture Tune a video concepts library's profile picture Keras Dreambooth Event's profile picture AI Zero to Hero's profile picture Stable Diffusion Dreambooth Concepts Library's profile picture The Waifu Research Department's profile picture AI Indonesia Community's profile picture M.O.F.U.'s profile picture ShoukanLabs's profile picture Blog-explorers's profile picture BangumiBase's profile picture CyberHarem's profile picture Touhou AI Experimental Group (MOFU)'s profile picture Tensor Diffusion's profile picture OpenOrca's profile picture huggingPartyParis's profile picture Multi๐Ÿค–Transformers's profile picture Team Tonic's profile picture That Time I got Reincarnated as a Hugging Face Organization's profile picture ZeroGPU Explorers's profile picture LocalLLaMA's profile picture BrainPulse's profile picture Argilla Explorers's profile picture MLX Community's profile picture INNOVA AI's profile picture Narra's profile picture Social Post Explorers's profile picture C4AI Community's profile picture Tunisia.AI's profile picture M4-ai's profile picture Dev Mode Explorers's profile picture Chinese LLMs on Hugging Face's profile picture Paris AI Running Club's profile picture AI4Health's profile picture Stable Diffusion Community (Unofficial, Non-profit)'s profile picture Hugging Face for Legal's profile picture Hugging Face Discord Community's profile picture phxia's profile picture random cool awesome garbage's profile picture Arilio's profile picture Data Tonic (Alignment Lab)'s profile picture Nerdy Face's profile picture open/ acc's profile picture Data Is Better Together Contributor's profile picture Donut Earthers ๐Ÿฉ's profile picture

not-lain's activity

reacted to hexgrad's post with ๐Ÿ”ฅ about 6 hours ago
view post
Post
2540
self.brag(): Kokoro finally got 300 votes in Pendrokar/TTS-Spaces-Arena after @Pendrokar was kind enough to add it 3 weeks ago.
Discounting the small sample size of votes, I think it is safe to say that hexgrad/Kokoro-TTS is currently a top 3 model among the contenders in that Arena. This is notable because:
- At 82M params, Kokoro is one of the smaller models in the Arena
- MeloTTS has 52M params
- F5 TTS has 330M params
- XTTSv2 has 467M params
ยท
reacted to loubnabnl's post with ๐Ÿ”ฅ 7 days ago
view post
Post
1311
Making SmolLM2 reproducible: open-sourcing our training & evaluation toolkit ๐Ÿ› ๏ธ https://github.com/huggingface/smollm/

- Pre-training code with nanotron
- Evaluation suite with lighteval
- Synthetic data generation using distilabel (powers our new SFT dataset HuggingFaceTB/smoltalk)
- Post-training scripts with TRL & the alignment handbook
- On-device tools with llama.cpp for summarization, rewriting & agents

Apache 2.0 licensed. V2 pre-training data mix coming soon!

Which other tools should we add next?
reacted to victor's post with ๐Ÿ”ฅ 8 days ago
view post
Post
1967
Perfect example of why Qwen/Qwen2.5-Coder-32B-Instruct is insane?

Introducing: AI Video Composer ๐Ÿ”ฅ
huggingface-projects/ai-video-composer

Drag and drop your assets (images/videos/audios) to create any video you want using natural language!

It works by asking the model to output a valid FFMPEG and this can be quite complex but most of the time Qwen2.5-Coder-32B gets it right (that thing is a beast). It's an update of an old project made with GPT4 and it was almost impossible to make it work with open models back then (~1.5 years ago), but not anymore, let's go open weights ๐Ÿš€.
reacted to luigi12345's post with ๐Ÿ‘ 8 days ago
view post
Post
3634
MinimalScrap
Only Free Dependencies. Save it.It is quite useful uh.


!pip install googlesearch-python requests
from googlesearch import search
import requests
query = "Glaucoma"
for url in search(f"{query} site:nih.gov filetype:pdf", 20):
    if url.endswith(".pdf"):
        with open(url.split("/")[-1], "wb") as f: f.write(requests.get(url).content)
        print("โœ…" + url.split("/")[-1])
print("Done!")

reacted to merve's post with โค๏ธ 11 days ago
view post
Post
2918
your hugging face profile now has your recent activities ๐Ÿค—
replied to cfahlgren1's post 13 days ago
reacted to davanstrien's post with โค๏ธ 13 days ago
reacted to sayakpaul's post with ๐Ÿš€โค๏ธ 13 days ago
view post
Post
2446
It's been a while we shipped native quantization support in diffusers ๐Ÿงจ

We currently support bistandbytes as the official backend but using others like torchao is already very simple.

This post is just a reminder of what's possible:

1. Loading a model with a quantization config
2. Saving a model with quantization config
3. Loading a pre-quantized model
4. enable_model_cpu_offload()
5. Training and loading LoRAs into quantized checkpoints

Docs:
https://huggingface.co/docs/diffusers/main/en/quantization/bitsandbytes
  • 1 reply
ยท
reacted to merve's post with ๐Ÿ‘€๐Ÿ”ฅ 15 days ago
view post
Post
4836
OmniVision-968M: a new local VLM for edge devices, fast & small but performant
๐Ÿ’จ a new vision language model with 9x less image tokens, super efficient
๐Ÿ“– aligned with DPO for reducing hallucinations
โšก๏ธ Apache 2.0 license ๐Ÿ”ฅ

Demo hf.co/spaces/NexaAIDev/omnivlm-dpo-demo
Model NexaAIDev/omnivision-968M
  • 4 replies
ยท
reacted to BlinkDL's post with ๐Ÿ”ฅ 18 days ago
view post
Post
3064
RWKV-6-world-v3 (+3.1T tokens) is our best multilingual 7B model as of now: BlinkDL/rwkv-6-world

It's 100% RNN and attention-free. MMLU 54.2% (previous world-v2.1 = 47.9%. note: without eval-boosting tricks such as annealing).

RWKV-7-world-v4 soon :)
reacted to m-ric's post with โค๏ธโค๏ธ๐Ÿ”ฅ 18 days ago
view post
Post
3698
๐—ง๐—ต๐—ฒ ๐—ป๐—ฒ๐˜…๐˜ ๐—ฏ๐—ถ๐—ด ๐˜€๐—ผ๐—ฐ๐—ถ๐—ฎ๐—น ๐—ป๐—ฒ๐˜๐˜„๐—ผ๐—ฟ๐—ธ ๐—ถ๐˜€ ๐—ป๐—ผ๐˜ ๐Ÿฆ‹, ๐—ถ๐˜'๐˜€ ๐—›๐˜‚๐—ฏ ๐—ฃ๐—ผ๐˜€๐˜๐˜€! [INSERT STONKS MEME WITH LASER EYES]

See below: I got 105k impressions since regularly posting Hub Posts, coming close to my 275k on Twitter!

โš™๏ธ Computed with the great dataset maxiw/hf-posts
โš™๏ธ Thanks to Qwen2.5-Coder-32B for showing me how to access dict attributes in a SQL request!

cc @merve who's far in front of me
ยท
posted an update 18 days ago
view post
Post
1445
ever wondered how you can make an API call to a visual-question-answering model without sending an image url ๐Ÿ‘€

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.
๐Ÿ”— https://github.com/not-lain/loadimg

API request example ๐Ÿ› ๏ธ:
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="")
reacted to louisbrulenaudet's post with ๐Ÿค— 18 days ago
view post
Post
1625
Iโ€™ve published a new dataset to simplify model merging ๐Ÿค—

This dataset facilitates the search for compatible architectures for model merging with @arcee_aiโ€™s mergekit, streamlining the automation of high-performance merge searches ๐Ÿ“–

Dataset : louisbrulenaudet/mergekit-configs
reacted to DavidGF's post with ๐Ÿ”ฅ 27 days ago
view post
Post
2991
๐ŸŽ‰ Celebrating One Year of #SauerkrautLM with Two Groundbreaking Releases!

We're thrilled to announce the release of SauerkrautLM-v2-14b in two specialized versions: VAGOsolutions/SauerkrautLM-v2-14b-SFT and VAGOsolutions/SauerkrautLM-v2-14b-DPO. Built on the robust Qwen2.5-14B foundation, these models represent a significant leap forward in multilingual AI capabilities.

๐Ÿ”ฌ Technical Breakthroughs:
๐Ÿ’  Innovative three-phase Fine-Tuning approach
๐Ÿ’  Two-step Spectrum SFT + one-step Spectrum DPO optimization phase for enhanced performance
๐Ÿ’  Balance of German and English language capabilities
๐Ÿ’  Advanced function calling - almost on par with Claude-3.5-Sonnet-20240620

๐Ÿ‡ฉ๐Ÿ‡ช German Language Excellence:
What sets this release apart is our unique achievement in simultaneously improving both German and English capabilities. Through our specialized training approach with over 1.2B tokens across two phases, we've managed to:
๐Ÿ’  Enhance German language understanding and generation (SFT Version > DPO Version)
๐Ÿ’  Maintain authentic German linguistic nuances
๐Ÿ’  Improve cross-lingual capabilities
๐Ÿ’  Preserve cultural context awareness

๐Ÿ“Š Training Innovation:
Our three-phase approach targeted specific layer percentages (15%, 20% and 25%) with carefully curated datasets, including:
๐Ÿ’  Mathematics-focused content (proprietary classifier-selected)
๐Ÿ’  High-quality German training data
๐Ÿ’  Specialized function calling datasets
๐Ÿ’  Premium multilingual content

๐ŸŽ Community Contribution:
We're also releasing two new datasets in a few days:
1๏ธโƒฃ SauerkrautLM-Fermented-GER-DPO: 3,300 high-quality German training samples
2๏ธโƒฃ SauerkrautLM-Fermented-Irrelevance-GER-DPO: 2,000 specialized samples for optimized function call irrelevance handling

Thank you to our incredible community and partners who have supported us throughout this journey. Here's to another year of AI innovation!ย ๐Ÿš€
reacted to reach-vb's post with ๐Ÿ”ฅ๐Ÿš€ 28 days ago
view post
Post
2961
Smol models ftw! AMD released AMD OLMo 1B - beats OpenELM, tiny llama on MT Bench, Alpaca Eval - Apache 2.0 licensed ๐Ÿ”ฅ

> Trained with 1.3 trillion (dolma 1.7) tokens on 16 nodes, each with 4 MI250 GPUs

> Three checkpoints:

- AMD OLMo 1B: Pre-trained model
- AMD OLMo 1B SFT: Supervised fine-tuned on Tulu V2, OpenHermes-2.5, WebInstructSub, and Code-Feedback datasets
- AMD OLMo 1B SFT DPO: Aligned with human preferences using Direct Preference Optimization (DPO) on UltraFeedback dataset

Key Insights:
> Pre-trained with less than half the tokens of OLMo-1B
> Post-training steps include two-phase SFT and DPO alignment
> Data for SFT:
- Phase 1: Tulu V2
- Phase 2: OpenHermes-2.5, WebInstructSub, and Code-Feedback

> Model checkpoints on the Hub & Integrated with Transformers โšก๏ธ

Congratulations & kudos to AMD on a brilliant smol model release! ๐Ÿค—

amd/amd-olmo-6723e7d04a49116d8ec95070