Discover the newest Hugging Face models on Azure AI! With 20+ models added in July, including multilingual and biomedical models, there's so much to explore. Dive into the world of AI and enhance your applications today! #LearnConnectBuildh
https://techcommunity.microsoft.com/t5/ai-ai-platform-blog/new-hugging-face-models-on-azure-ai-multilingual-slm-and-biomed/ba-p/4211881?wt.mc_id=twitter_4211881_organicsocial_reactor

TECHCOMMUNITY.MICROSOFT.COM

New Hugging Face Models on Azure AI: Multilingual, SLM and BioMed- July 2024 Update

In May, we announced a deepened partnership with Hugging Face and we continue to add more leading-edge Hugging Face models to the Azure AI model catalog on a..

AI unicorn Hugging Face acquires XetHub to manage huge AI models, aiming to host hundreds of millions. Meta's Llama 3.1 has 405B parameters, driving the need for more scalable solutions. XetHub's tools for efficient data management will integrate into Hugging Face's platform. #AI

Brief backstory: Before diving into AI, I spent over a decade working in ecological fields such as the conservation corps, biodynamic farming, and natural habitat restoration. This background instilled in me a deep concern about the environmental impact of scaling AI without sustainable practices.

Driven by this concern, I've spent months planning and experimenting to make my AI work more eco-friendly. I'm thrilled to announce that I've successfully transitioned my entire operation to run on 100% sustainable solar power!

How good are you at spotting AI-generated images?

Find out by playing Fake Insects 🐞 a Game where you need to identify which insects are fake (AI generated). Good luck & share your best score in the comments!

Wrote a blog post with some ideas about prompt engineering

https://huggingface.co/blog/KnutJaegersberg/first-principles-prompt-engineering

huggingface.co

Perspectives for first principles prompt engineering

A Blog post by Knut Jägersberg on Hugging Face

🚀 We’re excited to launch Ghost 8B Beta (1608), a top-performing language model with unmatched multilingual support and cost efficiency.

Key Highlights:
- Superior Performance: Outperforms Llama 3.1 8B Instruct, GPT-3.5 Turbo, Claude 3 Opus, GPT-4, and more in winrate scores.
- Expanded Language Support: Now supports 16 languages, including English, Vietnamese, Spanish, Chinese, and more.
- Enhanced Capabilities: Improved math, reasoning, and instruction-following for better task handling.

With two context options (8k and 128k), Ghost 8B Beta is perfect for complex, multilingual applications, balancing power and cost-effectiveness.

🔗 Learn More: https://ghost-x.org/docs/models/ghost-8b-beta
ghost-x/ghost-8b-beta-668ead6179f93be717db4542

Ghost X

Ghost 8B Beta

A large language model was developed with goals including excellent multilingual support, superior knowledge capabilities and cost efficiency.

🔔 Release: small-text v1.4.1

The new release contains some smaller bugfixes. Check it out!

Github: https://github.com/webis-de/small-text
Paper:
Small-Text: Active Learning for Text Classification in Python (2107.10314)

GitHub

GitHub - webis-de/small-text: Active Learning for Text Classification in Python

Active Learning for Text Classification in Python. Contribute to webis-de/small-text development by creating an account on GitHub.

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

GitHub

GitHub - nkasmanoff/ft-flow: Synthetic data to inference for LLM finetuning

Synthetic data to inference for LLM finetuning. Contribute to nkasmanoff/ft-flow development by creating an account on GitHub.

ResShift 1-Click Windows, RunPod, Massed Compute, Kaggle Installers with Amazing Gradio APP and Batch Image Processing. ResShift is Efficient Diffusion Model for Image Super-resolution by Residual Shifting (NeurIPS 2023, Spotlight).


Official Repo : https://github.com/zsyOAOA/ResShift

I have developed a very advanced Gradio APP.

Developed APP Scripts and Installers : https://www.patreon.com/posts/110331752

Features

It supports following tasks:

Real-world image super-resolution

Bicubic (resize by Matlab) image super-resolution

Blind Face Restoration

Automatically saving all generated image with same name + numbering if necessary

Randomize seed feature for each generation

Batch image processing - give input and output folder paths and it batch process all images and saves

1-Click to install on Windows, RunPod, Massed Compute and Kaggle (free account)

Windows Requirements

Python 3.10, FFmpeg, Cuda 11.8, C++ tools and Git

If it doesn't work make sure to below tutorial and install everything exactly as shown in this below tutorial

https://youtu.be/-NjNy7afOQ0

How to Install on Windows

Make sure that you have the above requirements

Extract files into a folder like c:/reshift_v1

Double click Windows_Install.bat and it will automatically install everything for you with an isolated virtual environment folder (VENV)

After that double click Windows_Start_app.bat and start the app

When you first time use a task it will download necessary models (all under 500 MB) into accurate folders

If during download it fails, file gets corrupted sadly it doesn't verify that so delete files inside weights and restart

How to Install on RunPod, Massed Compute, Kaggle

Follow the Massed_Compute_Instructions_READ.txt and Runpod_Instructions_READ.txt

For Kaggle follow the notebook written steps

An example video of how to use my RunPod, Massed Compute scripts and Kaggle notebook can be seen

https://youtu.be/wG7oPp01COg https://cdn-uploads.huggingface.co/production/uploads/6345bd89fe134dfd7a0dba40/K7p-mZHsz0BrVH0_DyfDa.png

GitHub

GitHub - zsyOAOA/ResShift: ResShift: Efficient Diffusion Model for Image Super-resolution by Residual Shifting (NeurIPS@2023 Spotlight…

ResShift: Efficient Diffusion Model for Image Super-resolution by Residual Shifting (NeurIPS@2023 Spotlight, TPAMI@2024) - zsyOAOA/ResShift

Click to view multi-image results on Mantis Eval, BLINK Val, Mathverse mv, Sciverse mv, MIRB.
Click to view video results on Video-MME and Video-ChatGPT.
Click to view few-shot results on TextVQA, VizWiz, VQAv2, OK-VQA.
Examples
https://github.com/OpenBMB/MiniCPM-V/raw/main/assets/minicpmv2_6/multi_img-bike.png
https://github.com/OpenBMB/MiniCPM-V/raw/main/assets/minicpmv2_6/multi_img-code.png
https://github.com/OpenBMB/MiniCPM-V/raw/main/assets/minicpmv2_6/ICL-Mem.png
Click to view more cases.
We deploy MiniCPM-V 2.6 on end devices. The demo video is the raw screen recording on a iPad Pro without edition.
https://github.com/OpenBMB/MiniCPM-V/raw/main/assets/gif_cases/ai.gif
https://github.com/OpenBMB/MiniCPM-V/raw/main/assets/gif_cases/ticket.gif
https://cdn-uploads.huggingface.co/production/uploads/64abc4aa6cadc7aca585dddf/mXAEFQFqNd4nnvPk7r5eX.mp4
Demo
Click here to try the Demo of MiniCPM-V 2.6.

https://cdn-uploads.huggingface.co/production/uploads/64abc4aa6cadc7aca585dddf/QVl0iPtT5aUhlvViyEpgs.png Single image results on OpenCompass, MME, MMVet, OCRBench, MMMU, MathVista, MMB, AI2D, TextVQA, DocVQA, HallusionBench, Object HalBench:

* We evaluate this benchmark using chain-of-thought prompting.

+ Token Density: number of pixels encoded into each visual token at maximum resolution, i.e., # pixels at maximum resolution / # visual tokens.

Note: For proprietary models, we calculate token density based on the image encoding charging strategy defined in the official API documentation, which provides an upper-bound estimation.

Click to view multi-image results on Mantis Eval, BLINK Val, Mathverse mv, Sciverse mv, MIRB.
Click to view video results on Video-MME and Video-ChatGPT.
Click to view few-shot results on TextVQA, VizWiz, VQAv2, OK-VQA.
Examples

💫 Easy Usage. MiniCPM-V 2.6 can be easily used in various ways: (1) llama.cpp and ollama support for efficient CPU inference on local devices, (2) int4 and GGUF format quantized models in 16 sizes, (3) vLLM support for high-throughput and memory-efficient inference, (4) fine-tuning on new domains and tasks, (5) quick local WebUI demo setup with Gradio and (6) online web demo.https://github.com/OpenBMB/MiniCPM-V/raw/main/assets/radar_final.png

🚀 Superior Efficiency. In addition to its friendly size, MiniCPM-V 2.6 also shows state-of-the-art token density (i.e., number of pixels encoded into each visual token). It produces only 640 tokens when processing a 1.8M pixel image, which is 75% fewer than most models. This directly improves the inference speed, first-token latency, memory usage, and power consumption. As a result, MiniCPM-V 2.6 can efficiently support real-time video understanding on end-side devices such as iPad.

💪 Strong OCR Capability and Others. MiniCPM-V 2.6 can process images with any aspect ratio and up to 1.8 million pixels (e.g., 1344x1344). It achieves state-of-the-art performance on OCRBench, surpassing proprietary models such as GPT-4o, GPT-4V, and Gemini 1.5 Pro. Based on the the latest RLAIF-V and VisCPM techniques, it features trustworthy behaviors, with significantly lower hallucination rates than GPT-4o and GPT-4V on Object HalBench, and supports multilingual capabilities on English, Chinese, German, French, Italian, Korean, etc.

🎬 Video Understanding. MiniCPM-V 2.6 can also accept video inputs, performing conversation and providing dense captions for spatial-temporal information. It outperforms GPT-4V, Claude 3.5 Sonnet and LLaVA-NeXT-Video-34B on Video-MME with/without subtitles.

🖼 Multi Image Understanding and In-context Learning. MiniCPM-V 2.6 can also perform conversation and reasoning over multiple images. It achieves state-of-the-art performance on popular multi-image benchmarks such as Mantis-Eval, BLINK, Mathverse mv and Sciverse mv, and also shows promising in-context learning capability.

🔥 Leading Performance. MiniCPM-V 2.6 achieves an average score of 65.2 on the latest version of OpenCompass, a comprehensive evaluation over 8 popular benchmarks. With only 8B parameters, it surpasses widely used proprietary models like GPT-4o mini, GPT-4V, Gemini 1.5 Pro, and Claude 3.5 Sonnet for single image understanding.

Level MLLM for Single Image, Multi Image and Video on Your Phone
GitHub | Demo

MiniCPM-V 2.6
MiniCPM-V 2.6 is the latest and most capable model in the MiniCPM-V series. The model is built on SigLip-400M and Qwen2-7B with a total of 8B parameters. It exhibits a significant performance improvement over MiniCPM-Llama3-V 2.5, and introduces new features for multi-image and video understanding. Notable features of MiniCPM-V 2.6 include:

New SmolLM-1.7B-Instruct
SmolLM is a series of small language models available in three sizes: 135M, 360M, and 1.7B parameters.

These models are pre-trained on SmolLM-Corpus, a curated collection of high-quality educational and synthetic data designed for training LLMs. For further details, we refer to our blogpost.

To build SmolLM-Instruct, we finetuned the base models on publicly available datasets.
https://huggingface.co/HuggingFaceTB/SmolLM-1.7B-Instruct-v0.2

1/4 Reproducing research results in ML is hard: no code, vague descriptions, noisy results.A lot of effort
@huggingface
goes into making new methods available for the community, thus we wrote a blog with the challenges and strategies on the example of
@GoogleAI
’s Infini-Attention
2/4 We attempted to reproduce Infini-Attention and found it generates content related to earlier segments, but it isn’t good enough to recall the needle in the haystack. We also faced convergence issues and wanted to share how we debugged them.

Link: http://huggingface.co/blog/infini-attention

huggingface.co

A failed experiment: Infini-Attention, and why we should keep trying?

We’re on a journey to advance and democratize artificial intelligence through open source and open science.