Hugging Face's logo
Adam Molnar's picture
TFLOPS icon 0.4 TFLOPS
134 657 562

Adam Molnar

lunarflu
Chris4K's profile picture multimodalart's profile picture MWilinski's profile picture
ยท

AI & ML interests

join the Hugging Face discord! hf.co/discord/join

Organizations

Hugging Face's profile picture Society & Ethics's profile picture Gradio's profile picture OpenDILab's profile picture Turing's Solutions's profile picture lora concepts library's profile picture Open-Source AI Meetup's profile picture Huggingface Projects's profile picture Arabic Machine Learning 's profile picture Pseudo Lab's profile picture Keras Dreambooth Event's profile picture Hugging Face OSS Metrics's profile picture Ontocord's M*DEL's profile picture The Waifu Research Department's profile picture M.O.F.U.'s profile picture Blog-explorers's profile picture OpenSky's profile picture Hugging Face for Computer Vision's profile picture CyberHarem's profile picture Touhou AI Experimental Group (MOFU)'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 hf-qa-bot's profile picture Journalists on Hugging Face's profile picture MLX Community's profile picture the collabage patch's profile picture INNOVA AI's profile picture Narra's profile picture Social Post Explorers's profile picture Quasar Research's profile picture Hugging Face for Legal's profile picture Hugging Face Discord Community's profile picture

lunarflu's activity

reacted to merve's post with โค๏ธ๐Ÿ‘€ 17 days ago
view post
Post
2381
Lotus ๐Ÿชท is a new foundation model on monocular depth estimation โœจ
Compared to previous diffusion-based MDE models, Lotus is modified for dense prediction tasks
Authors also released a model for normal prediction ๐Ÿค—
Find everything in this collection merve/lotus-6718fb957dc1c85a47ca1210
reacted to THUdyh's post with ๐Ÿ”ฅ 17 days ago
reacted to daniel-de-leon's post with ๐Ÿ”ฅ 17 days ago
view post
Post
2380
As the rapid adoption of chat bots and QandA models continues, so do the concerns for their reliability and safety. In response to this, many state-of-the-art models are being tuned to act as Safety Guardrails to protect against malicious usage and avoid undesired, harmful output. I published a Hugging Face blog introducing a simple, proof-of-concept, RoBERTa-based LLM that my team and I finetuned to detect toxic prompt inputs into chat-style LLMs. The article explores some of the tradeoffs of fine-tuning larger decoder vs. smaller encoder models and asks the question if "simpler is better" in the arena of toxic prompt detection.

๐Ÿ”— to blog: https://huggingface.co/blog/daniel-de-leon/toxic-prompt-roberta
๐Ÿ”— to model: Intel/toxic-prompt-roberta
๐Ÿ”— to OPEA microservice: https://github.com/opea-project/GenAIComps/tree/main/comps/guardrails/toxicity_detection

A huge thank you to my colleagues that helped contribute: @qgao007 , @mitalipo , @ashahba and Fahim Mohammad
reacted to TheStinger's post with โค๏ธ 17 days ago
reacted to John6666's post with โค๏ธ about 1 month ago
view post
Post
7200
@victor @not-lain There has been a sudden and unusual outbreak of spam postings on the HF Forum that seem to be aimed at relaying online videos and commenting on them. It is also spanning multiple languages for some reason. I've flagged it too, but I'm not sure if the staff will be able to keep up with the manual measures in the future.
  • 1 reply
ยท
reacted to sequelbox's post with ๐Ÿ”ฅ about 1 month ago
reacted to zamal's post with ๐Ÿš€ about 1 month ago
view post
Post
1932
๐Ÿš€ New Model Release: zamal/Molmo-7B-GPTQ-4bit ๐Ÿš€

Hello lovely community,

zamal/Molmo-7B-GPTQ-4bit model is now available for all! This model has been highly quantized, reducing its size by almost six times. It now occupies significantly less space and vRAM, making it perfect for deployment on resource-constrained devices without compromising performance.

Now we get:
Efficient Performance: Maintains high accuracy while being highly quantized.
Reduced Size: The model size is reduced by nearly six times, optimizing storage and memory usage.
Versatile Application: Ideal for integrating a powerful visual language model into various projects particularly multi rag chains.
Check it out!

  • 1 reply
ยท
reacted to singhsidhukuldeep's post with ๐Ÿง  about 2 months ago
view post
Post
1467
Researchers from @GoogleDeepMind have introduced "Michelangelo" โ€” a novel framework for evaluating large language models on long-context reasoning tasks beyond simple retrieval.

They have proposed three minimal tasks to test different aspects of long-context reasoning:
- Latent List: Tracking a Python list's state over many operations.
- MRCR: Multi-round coreference resolution in conversations.
- IDK: Determining if an answer exists in a long context.

They found significant performance drop-offs before 32K tokens on these tasks, indicating room for improvement in long-context reasoning.

Here are the key steps for creating the Michelangelo long-context evaluations:

1. Develop the Latent Structure Queries (LSQ) framework:
- Create a framework for generating long-context evaluations that can be extended arbitrarily in length and complexity.
- Ensure the framework measures capabilities beyond simple retrieval.

2. Design minimal tasks using the LSQ framework:
- Create tasks that test different aspects of long-context reasoning.
- Ensure tasks are minimally complex while still challenging for current models.

3. Implement the Latent List task:
- Create a Python list-based task with operations that modify the list.
- Include relevant and irrelevant operations to test model understanding.
- Develop view operations to query the final state of the list.

4. Implement the Multi-Round Coreference Resolution (MRCR) task:
- Generate conversations with user requests and model responses on various topics.
- Place specific requests randomly in the context.
- Require models to reproduce outputs based on queries about the conversation.

5. Implement the IDK task:
- Create contexts with invented stories or information.
- Develop questions that may or may not have answers in the context.
- Include multiple-choice options, always including "I don't know" as an option.

More in comments...
  • 1 reply
ยท
reacted to 1aurent's post with ๐Ÿ”ฅ 2 months ago
view post
Post
1051
Hey everyone ๐Ÿค—!
We (finegrain) have created some custom ComfyUI nodes to use our refiners micro-framework inside comfy! ๐ŸŽ‰

We only support our new Box Segmenter at the moment, but we're thinking of adding more nodes since there seems to be a demand for it. We leverage the new (beta) Comfy Registry to host our nodes. They are available at: https://registry.comfy.org/publishers/finegrain/nodes/comfyui-refiners. You can install them by running:
comfy node registry-install comfyui-refiners

Or by unzipping the archive you can download by clicking "Download Latest" into your custom_nodes comfy folder.
We are eager to hear your feedbacks and suggestions for new nodes and how you'll use them! ๐Ÿ™
replied to vilarin's post 2 months ago
reacted to vilarin's post with โค๏ธ 2 months ago
view post
Post
5965
๐Ÿคฉ Amazing day. AWPortrait-FL finally here!
๐Ÿฆ– 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.

๐Ÿค—Model: Shakker-Labs/AWPortrait-FL

๐Ÿ™‡Demo: vilarin/flux-labs

ยท
reacted to nkasmanoff's post with ๐Ÿ‘€ 3 months ago
view post
Post
1817
Put together a small repo showing how to go from making your own fine-tuning dataset w/ services like Groq & Together to publishing that model on ollama.

In my case I fine-tuned SmolLM-360M to be a better assistant for my Pi-Card (previous post) project.

Check it out!
https://github.com/nkasmanoff/ft-flow
reacted to davanstrien's post with ๐Ÿค— 3 months ago
view post
Post
3145
๐Ÿš€ Introducing Hugging Face Similar: a Chrome extension to find relevant datasets!

โœจ Adds a "Similar Datasets" section to Hugging Face dataset pages
๐Ÿ” Recommendations based on dataset READMEs
๐Ÿ—๏ธ Powered by https://huggingface.co/chromadb and https://huggingface.co/Snowflake embeddings.

You can try it here: https://chromewebstore.google.com/detail/hugging-face-similar/aijelnjllajooinkcpkpbhckbghghpnl?authuser=0&hl=en.

I am very happy to get feedback on whether this could be useful or not ๐Ÿค—
ยท
posted an update 3 months ago
posted an update 4 months ago
view post
Post
1804
Cool things this week from @huggingface !

๐ŸŒŽAI math olympiad winner NuminaMath is here!
๐Ÿค—Announcing New Hugging Face and Keras NLP integration
โœจUI overhaul to HF tokens!
๐ŸงŠ Embed our dataset viewer on any webpage!

https://huggingface.co/blog/winning-aimo-progress-prize
https://huggingface.co/blog/keras-nlp-integration
https://huggingface.co/settings/tokens
https://x.com/julien_c/status/1812099420726456457

Check out the full list on our discord! ๐Ÿ‘‡
https://discord.com/invite/JfAtkvEtRb
reacted to Niansuh's post with ๐Ÿ”ฅ 4 months ago
view post
Post
2553
Introducing Plugins in NiansuhAI (on July 20, 2024)

Plugin Names:
1. WebSearch: Tool for searching the web using search engines.
2. Calculator: Helps evaluate mathematical expressions; extends the base Tool class.
3. WebBrowser: Interacts with web pages to extract information or summarize content.
4. Wikipedia: Retrieves data from Wikipedia using its API.
5. Arxiv: Searches and fetches article information from Arxiv.
6. WolframAlphaTool: Answers questions on Math, Science, Technology, Culture, Society, and Everyday Life.

Similar to https://hf.co/chat
reacted to tomaarsen's post with ๐Ÿ”ฅ 4 months ago
view post
Post
3882
@Omartificial-Intelligence-Space has trained and released 6 Arabic embedding models for semantic similarity. 4 of them outperform all previous models on the STS17 Arabic-Arabic task!

๐Ÿ“š Trained on a large dataset of 558k Arabic triplets translated from the AllNLI triplet dataset: Omartificial-Intelligence-Space/Arabic-NLi-Triplet
6๏ธโƒฃ 6 different base models: AraBERT, MarBERT, LaBSE, MiniLM, paraphrase-multilingual-mpnet-base, mpnet-base, ranging from 109M to 471M parameters.
๐Ÿช† Trained with a Matryoshka loss, allowing you to truncate embeddings with minimal performance loss: smaller embeddings are faster to compare.
๐Ÿ“ˆ Outperforms all commonly used multilingual models like intfloat/multilingual-e5-large, sentence-transformers/paraphrase-multilingual-mpnet-base-v2, and sentence-transformers/LaBSE.

Check them out here:
- Omartificial-Intelligence-Space/Arabic-mpnet-base-all-nli-triplet
- Omartificial-Intelligence-Space/Arabic-all-nli-triplet-Matryoshka
- Omartificial-Intelligence-Space/Arabert-all-nli-triplet-Matryoshka
- Omartificial-Intelligence-Space/Arabic-labse-Matryoshka
- Omartificial-Intelligence-Space/Marbert-all-nli-triplet-Matryoshka
- Omartificial-Intelligence-Space/Arabic-MiniLM-L12-v2-all-nli-triplet
Or the collection with all: Omartificial-Intelligence-Space/arabic-matryoshka-embedding-models-666f764d3b570f44d7f77d4e

My personal favourite is likely Omartificial-Intelligence-Space/Arabert-all-nli-triplet-Matryoshka: a very efficient 135M parameters & scores #1 on mteb/leaderboard.
  • 1 reply
ยท
reacted to qnguyen3's post with ๐Ÿ”ฅ 4 months ago
reacted to victor's post with โค๏ธ 4 months ago