Hugging Face – Posts

Join the conversation

Join the community of Machine Learners and AI enthusiasts.

All HF Hub posts

Wauplin

posted an update 1 day ago

Post

2667

🚀 Exciting News! 🚀

We've just released 𝚑𝚞𝚐𝚐𝚒𝚗𝚐𝚏𝚊𝚌𝚎_𝚑𝚞𝚋 v0.25.0 and it's packed with powerful new features and improvements!

✨ 𝗧𝗼𝗽 𝗛𝗶𝗴𝗵𝗹𝗶𝗴𝗵𝘁𝘀:

• 📁 𝗨𝗽𝗹𝗼𝗮𝗱 𝗹𝗮𝗿𝗴𝗲 𝗳𝗼𝗹𝗱𝗲𝗿𝘀 with ease using huggingface-cli upload-large-folder. Designed for your massive models and datasets. Much recommended if you struggle to upload your Llama 70B fine-tuned model 🤡
• 🔎 𝗦𝗲𝗮𝗿𝗰𝗵 𝗔𝗣𝗜: new search filters (gated status, inference status) and fetch trending score.
• ⚡𝗜𝗻𝗳𝗲𝗿𝗲𝗻𝗰𝗲𝗖𝗹𝗶𝗲𝗻𝘁: major improvements simplifying chat completions and handling async tasks better.

We’ve also introduced tons of bug fixes and quality-of-life improvements - thanks to the awesome contributions from our community! 💪

💡 Check out the release notes: Wauplin/huggingface_hub#8

Want to try it out? Install the release with:

pip install huggingface_hub==0.25.0

1 reply

m-ric

posted an update about 17 hours ago

Post

987

🔥 𝐐𝐰𝐞𝐧 𝐫𝐞𝐥𝐞𝐚𝐬𝐞𝐬 𝐭𝐡𝐞𝐢𝐫 𝟐.𝟓 𝐟𝐚𝐦𝐢𝐥𝐲 𝐨𝐟 𝐦𝐨𝐝𝐞𝐥𝐬: 𝐍𝐞𝐰 𝐒𝐎𝐓𝐀 𝐟𝐨𝐫 𝐚𝐥𝐥 𝐬𝐢𝐳𝐞𝐬 𝐮𝐩 𝐭𝐨 𝟕𝟐𝐁!

The Chinese LLM maker just dropped a flurry of different models, ensuring there will be a Qwen SOTA model for every application out there:
Qwen2.5: 0.5B, 1.5B, 3B, 7B, 14B, 32B, and 72B
Qwen2.5-Coder: 1.5B, 7B, and 32B on the way
Qwen2.5-Math: 1.5B, 7B, and 72B.

And they didn't sleep: the performance is top of the game for each weight category!

𝐊𝐞𝐲 𝐢𝐧𝐬𝐢𝐠𝐡𝐭𝐬:

🌐 All models have 𝟭𝟮𝟴𝗸 𝘁𝗼𝗸𝗲𝗻 𝗰𝗼𝗻𝘁𝗲𝘅𝘁 𝗹𝗲𝗻𝗴𝘁𝗵

📚 Models pre-trained on 18T tokens, even longer than the 15T of Llama-3

💪 The flagship 𝗤𝘄𝗲𝗻𝟮.𝟱-𝟳𝟮𝗕 𝗶𝘀 ~𝗰𝗼𝗺𝗽𝗲𝘁𝗶𝘁𝗶𝘃𝗲 𝘄𝗶𝘁𝗵 𝗟𝗹𝗮𝗺𝗮-𝟯.𝟭-𝟰𝟬𝟱𝗕, 𝗮𝗻𝗱 𝗵𝗮𝘀 𝗮 𝟯-𝟱% 𝗺𝗮𝗿𝗴𝗶𝗻 𝗼𝗻 𝗟𝗹𝗮𝗺𝗮-𝟯.𝟭-𝟳𝟬𝗕 𝗼𝗻 𝗺𝗼𝘀𝘁 𝗯𝗲𝗻𝗰𝗵𝗺𝗮𝗿𝗸𝘀.

🇫🇷 On top of this, it 𝘁𝗮𝗸𝗲𝘀 𝘁𝗵𝗲 #𝟭 𝘀𝗽𝗼𝘁 𝗼𝗻 𝗺𝘂𝗹𝘁𝗶𝗹𝗶𝗻𝗴𝘂𝗮𝗹 𝘁𝗮𝘀𝗸𝘀 so it might become my standard for French

💻 Qwen2.5-Coder is only 7B but beats competing models up to 33B (DeeSeek-Coder 33B-Instruct). Let's wait for their 32B to come out!

🧮 Qwen2.5-Math sets a new high in the ratio of MATH benchmark score to # of parameters. They trained it by "aggregating more high-quality mathematical data, particularly in Chinese, from web sources, books, and codes across multiple recall cycles."

📄 Technical report to be released "very soon"

🔓 All models have the most permissive license apache2.0, except the 72B models that have a custom license mentioning "you can use it for free EXCEPT if your product has over 100M users"

🤗 All models are available on the HF Hub! ➡️ Qwen/qwen25-66e81a666513e518adb90d9e

2 replies

jeffboudier

posted an update 3 days ago

Post

3560

Pro Tip - if you're a Firefox user, you can set up Hugging Chat as integrated AI Assistant, with contextual links to summarize or simplify any text - handy!

In this short video I show how to set it up

2 replies

prithivMLmods

posted an update 1 day ago

Post

1353

I am experimenting with the Flux-Realism and Flux-Anime LoRA models, using the Flux.1-dev & schnell models as the base. The desired results improve significantly as the image lengths increase. 🎈

The demo for the respective trials is :\
- prithivMLmods/FLUX-REALISM
- prithivMLmods/FLUX-ANIME

Model :\
- prithivMLmods/Canopus-LoRA-Flux-FaceRealism
- prithivMLmods/Canopus-LoRA-Flux-Anime

Dataset:\
- prithivMLmods/Canopus-Realism-Minimalist
- https://4kwallpapers.com

2 replies

udaykc

posted an update 1 day ago

Post

1837

My way of understanding of AI:
Artificial Intelligence is a concept developed by human intelligence, where systems are designed to simulate human-like thinking, analysis, understanding, and creation, often performing tasks faster and more efficiently than humans.

Add your thoughts...

1 reply

KingNish

posted an update 2 days ago

Post

2277

Mistral Nemo is better than many models in 1st grader level reasoning.

joylarkin

posted an update 2 days ago

Post

2470

💬 Chat as a way to query SQL! The Airtrain AI team is happy to share a new Hugging Face Space that lets you interact with Hugging Face Hub datasets using a natural language chatbot. 🤗

Start Exploring 👉 airtrain-ai/hf-dataset-chat-to-sql

This Space is forked from davidberenstein1957/text-to-sql-hub-datasets by @davidberenstein1957 and features chat capability with improved table naming. The tool works with Hugging Face’s recently released in-browser DuckDB-based SQL query engine for datasets.

MoritzLaurer

posted an update about 15 hours ago

Post

554

Why would you fine-tune a model if you can just prompt an LLM? The new paper "What is the Role of Small Models in the LLM Era: A Survey" provides a nice pro/con overview. My go-to approach combines both:

1. Start testing an idea by prompting an LLM/VLM behind an API. It's fast and easy and I avoid wasting time on tuning a model on a task that might not make it into production anyways.

2. The LLM/VLM then needs to be manually validated. Anyone seriously considering putting AI into production has to do at least some manual validation. Setting up a good validation pipeline with a tool like Argilla is crucial and it can be reused for any future experiments. Note: you can use LLM-as-a-judge to automate some evals, but you always also need to validate the judge!

3. Based on this validation I can then (a) either just continue using the prompted LLM if it is accurate enough and it makes sense financially given my load; or (b) if the LLM is not accurate enough or too expensive to run in the long-run, I reuse the existing validation pipeline to annotate some additional data for fine-tuning a smaller model. This can be sped up by reusing & correcting synthetic data from the LLM (or just pure distillation).

Paper: https://arxiv.org/pdf/2409.06857
Argilla docs: https://docs.argilla.io/latest/
Argilla is also very easy to deploy with Hugging Face Spaces (or locally): https://huggingface.co/new-space?template=argilla%2Fargilla-template-space

MonsterMMORPG

posted an update about 21 hours ago

Post

785

How to Extract LoRA from FLUX Fine Tuning / DreamBooth Training Full Tutorial and Comparison Between Fine Tuning vs Extraction vs LoRA Training

Full article is here public post : https://www.patreon.com/posts/112335162

This was short on length so check out the full article - public post

Conclusions as below

Conclusions
With same training dataset (15 images used), same number of steps (all compared trainings are 150 epoch thus 2250 steps), almost same training duration, Fine Tuning / DreamBooth training of FLUX yields the very best results

So yes Fine Tuning is the much better than LoRA training itself

Amazing resemblance, quality with least amount of overfitting issue

Moreover, extracting a LoRA from Fine Tuned full checkpoint, yields way better results from LoRA training itself

Extracting LoRA from full trained checkpoints were yielding way better results in SD 1.5 and SDXL as well

Comparison of these 3 is made in Image 5 (check very top of the images to see)

640 Network Dimension (Rank) FP16 LoRA takes 6.1 GB disk space

You can also try 128 Network Dimension (Rank) FP16 and different LoRA strengths during inference to make it closer to Fine Tuned model

Moreover, you can try Resize LoRA feature of Kohya GUI but hopefully it will be my another research and article later

Image Raw Links
Image 1 : MonsterMMORPG/FLUX-Fine-Tuning-Grid-Tests

Image 2 : MonsterMMORPG/FLUX-Fine-Tuning-Grid-Tests

Image 3 : MonsterMMORPG/FLUX-Fine-Tuning-Grid-Tests

Image 4 : MonsterMMORPG/FLUX-Fine-Tuning-Grid-Tests

Image 5 : MonsterMMORPG/FLUX-Fine-Tuning-Grid-Tests

m-ric

posted an update 3 days ago

Post

1504

𝗔𝗿𝗲 𝗔𝗴𝗲𝗻𝘁𝘀 𝗰𝗮𝗽𝗮𝗯𝗹𝗲 𝗲𝗻𝗼𝘂𝗴𝗵 𝗳𝗼𝗿 𝗗𝗮𝘁𝗮 𝗦𝗰𝗶𝗲𝗻𝗰𝗲? ⇒ 𝗠𝗲𝗮𝘀𝘂𝗿𝗲 𝘁𝗵𝗲𝗶𝗿 𝗽𝗲𝗿𝗳𝗼𝗿𝗺𝗮𝗻𝗰𝗲 𝘄𝗶𝘁𝗵 𝗗𝗦𝗕𝗲𝗻𝗰𝗵 📊

A team from Tencent AI wanted to evaluate agentic systems on data science (DS) tasks : but they noticed that existing agentic benchmarks were severely limited in several aspects: they were limited to text and did not include tables or images, were only specific to certain packages, only performed exact match evaluation…

➡️ So they set out to build a much more exhaustive approach, to finally make the definitive DS agent benchmark.

𝗧𝗵𝗲 𝗗𝗦𝗕𝗲𝗻𝗰𝗵 𝗱𝗮𝘁𝗮𝘀𝗲𝘁
▪️DS bench has 466 data analysis tasks and 74 data modelling tasks
▪️The tasks are sourced from ModelOff and Kaggle, the platforms hosting the most popular data science competitions
▪️Difference with previous DS benchmarks:
❶ This benchmark leverages various modalities on top of text: images, Excel files, tables
❷ Complex tables: sometimes several tables should be leveraged to answer one question
❸ The context is richer, with longer descriptions.
▪️ Evaluation metrics : the benchmark is scored with an LLM as a judge, using a specific prompt.

𝗜𝗻𝘀𝗶𝗴𝗵𝘁𝘀 𝗳𝗿𝗼𝗺 𝗲𝘃𝗮𝗹𝘂𝗮𝘁𝗶𝗻𝗴 𝗮𝗴𝗲𝗻𝘁𝘀
▪️ Their evaluation confirms that using LLMs in an agent setup, for instance by allowing them to run a single step of code execution, is more costly (especially with multi-turn frameworks like autogen) but also much more performant than the vanilla LLM.
▪️ The sets of tasks solved by different models (like GPT-3.5 vs Llama-3-8B) has quite low overlap, which suggests that different models tend to try very different approches.

This new benchmark is really welcome, can't wait to try transformers agents on it! 🤗

Read their full paper 👉 DSBench: How Far Are Data Science Agents to Becoming Data Science Experts? (2409.07703)

Recently active users