Hugging Face's logo

Join the conversation

Join the community of Machine Learners and AI enthusiasts.

Sign Up

All HF Hub posts
openfreeΒ 
posted an update about 5 hours ago
view post
Post
726
πŸš€ Gemma3-R1984-27B: Next Generation Agentic AI Platform

Model Path: VIDraft/Gemma-3-R1984-27B
Space: VIDraft/Gemma-3-R1984-27B
git clone VIDraft/Gemma-3-R1984-27B

πŸ’« A New Frontier in AI Innovation
Gemma3-R1984-27B is a powerful agentic AI platform built on Microsoft's Gemma-3-27B model. It integrates state-of-the-art deep research via web search with multimodal file processing capabilities and handles long contexts up to 8,000 tokens. Designed for local deployment on independent servers using NVIDIA A100 GPUs, it provides high security and prevents data leakage.

πŸ”“ Uncensored and Unrestricted AI Experience
Gemma3-R1984-27B comes with all censorship restrictions removed, allowing users to operate any persona without limitations. The model perfectly implements various roles and characters according to users' creative requests, providing unrestricted responses that transcend the boundaries of conventional AI. This unlimited interaction opens infinite possibilities across research, creative work, entertainment, and many other fields.

✨ Key Features
πŸ–ΌοΈ Multimodal Processing

Images (PNG, JPG, JPEG, GIF, WEBP)
Videos (MP4)
Documents (PDF, CSV, TXT) and various other file formats

πŸ” Deep Research (Web Search)

Automatically extracts keywords from user queries
Utilizes SERPHouse API to retrieve up to 20 real-time search results
Incorporates multiple sources by explicitly citing them in responses

πŸ“š Long Context Handling

Capable of processing inputs up to 8,000 tokens
Ensures comprehensive analysis of lengthy documents or conversations

🧠 Robust Reasoning

Employs extended chain-of-thought reasoning for systematic and accurate answer generation

πŸ’Ό Use Cases

⚑ Fast-response conversational agents
πŸ“Š Document comparison and detailed analysis
πŸ‘οΈ Visual question answering from images and videos
πŸ”¬ Complex reasoning and research-based inquiries
Β·
openfreeΒ 
posted an update 2 days ago
view post
Post
4731
πŸš€ DeepSeek V3-0324 + Real-time Research Power! 🌐

Hello there! Today I'm excited to introduce an amazing tool based on the DeepSeek V3-0324 latest model. This isn't just another AI chatbotβ€”it's a true "research assistant" capable of real-time information retrieval and analysis!

openfree/Deepseek-v3-0324-Research

🧠 Key Strengths of DeepSeek V3-0324
DeepSeek V3-0324, provided by Fireworks AI, comes with these powerful advantages:

🎯 Superior Reasoning: Excellent ability to solve complex problems step-by-step
πŸ“š Extensive Knowledge: Deep understanding across various topics from comprehensive training

🧩 Context Awareness: Maintains long conversation contexts for consistent responses
🌍 Multilingual Support: Processes various languages effectively

πŸ”Ž Added Real-time "Deep Research" Capability!
The most exciting feature of this project is the implementation of real-time search functionality similar to ChatGPT's Browse with Bing or Perplexity AI! 🌟
How does it work?

πŸ“‹ Query Analysis: Analyzes questions to automatically extract optimal search keywords
🌐 Web Search: Utilizes advanced search technology to retrieve the latest information
πŸ§ͺ Result Analysis: Intelligently analyzes search results and evaluates relevance
πŸ’‘ Comprehensive Response: Combines freshly retrieved information with AI's existing knowledge

Key Benefits:

⏱️ Up-to-date Information: Always provides the latest data through real-time web searches
πŸ“Š Enhanced Reliability: Improves trustworthiness by citing information sources
πŸ”„ Overcoming Knowledge Limitations: Handles questions beyond the AI's training cutoff
πŸ› οΈ Research Efficiency: Processes everything from information retrieval to analysis in one go

πŸ–₯️ How to Use
It's simple! Just enable the "Deep Research" checkbox and ask your question. The AI will automatically search for and analyze relevant information to provide rich, informed answers.
  • 1 reply
Β·
giadapΒ 
posted an update about 20 hours ago
view post
Post
1016
We've all become experts at clicking "I agree" without a second thought. In my latest blog post, I explore why these traditional consent models are increasingly problematic in the age of generative AI.

I found three fundamental challenges:
- Scope problem: how can you know what you're agreeing to when AI could use your data in different ways?
- Temporality problem: once an AI system learns from your data, good luck trying to make it "unlearn" it.
- Autonomy trap: the data you share today could create systems that pigeonhole you tomorrow.

Individual users shouldn't bear all the responsibility, while big tech holds all the cards. We need better approaches to level the playing field, from collective advocacy and stronger technological safeguards to establishing "data fiduciaries" with a legal duty to protect our digital interests.

Available here: https://huggingface.co./blog/giadap/beyond-consent
nroggendorffΒ 
posted an update about 9 hours ago
view post
Post
604
I'm not really doing much on HuggingFace right now due to their new Docker space policies, so if you want to keep up with most of what I'm up to, follow my [instagram](https://sly.sh/ig)
chansungΒ 
posted an update 1 day ago
view post
Post
2715
simple guide on the recipe for GRPO on Open-R1 which is built on top of TRL

I think FastAPI wrapper of vLLM with WeightSyncWorker is pretty cool feature. Also, we have many predefined reward functions out of the box!
Β·
giux78Β 
posted an update about 12 hours ago
view post
Post
656
This is truly an inspirational story please help us spread the word, @clem , @thomwolf and everyone who supports open source AI.

A few weeks ago, @mmuffo94 and @cittiberto from indigo_ai launched the Chatbot Arena for the Italian language: https://indigo.ai/it/chatbot-arena-italia/.

To our surprise, among the top-ranked models is mii-llm/maestrale-chat-v0.4-beta a carefully fine-tuned version of mistralai/Mistral-7B-v0.1, developed by @efederici and @mferraretto from https://huggingface.co./mii-llm, and released nearly a year ago.

At this very moment, as shown in the screenshot, mii-llm/maestrale-chat-v0.4-beta is ranked 8th right between ChatGPT-4.5 and ChatGPT-4o.

It's likely that for several months, the best Italian speaking LLM has been an open source 7B model created by open source contributors and hardly anyone knew it.
  • 1 reply
Β·
luigi12345Β 
posted an update about 15 hours ago
view post
Post
632
πŸ”₯ ULTRA VIDEO COMPRESSION (300MB β†’ 3MB!)
ffmpeg -i input.mp4 -vcodec libx264 -crf 28 -vf "pad=ceil(iw/2)*2:ceil(ih/2)*2" -y output.mp4

-i β†’ Input ⚑️ -vcodec libx264 β†’ H.264 codec ⚑️ -crf 28 β†’ Compression (lower = better quality) ⚑️-vf pad=... β†’ Even dimensions ⚑️ -y β†’ Overwrite
  • 1 reply
Β·
tomaarsenΒ 
posted an update about 19 hours ago
view post
Post
892
‼️Sentence Transformers v4.0 is out! You can now train and finetune reranker models with multi-GPU training, bf16 support, loss logging, callbacks & much more. I also prove that finetuning on your domain helps much more than you might think.

1️⃣ Reranker Training Refactor
Reranker models can now be trained using an extensive trainer with a lot of powerful features:
- MultiGPU Training (Data Parallelism (DP) and Distributed Data Parallelism (DDP))
- bf16 training support; loss logging
- Evaluation datasets + evaluation loss
- Improved callback support + an excellent Weights & Biases integration
- Gradient checkpointing, gradient accumulation
- Model card generation
- Resuming from a training checkpoint without performance loss
- Hyperparameter Optimization
and much more!

Read my detailed blogpost to learn about the components that make up this new training approach: https://huggingface.co./blog/train-reranker
Notably, the release is fully backwards compatible: all deprecations are soft, meaning that they still work but emit a warning informing you how to upgrade.

2️⃣ New Reranker Losses
- 11 new losses:
- 2 traditional losses: BinaryCrossEntropy and CrossEntropy
- 2 distillation losses: MSE and MarginMSE
- 2 in-batch negatives losses: MNRL (a.k.a. InfoNCE) and CMNRL
- 5 learning to rank losses: Lambda, p-ListMLE, ListNet, RankNet, ListMLE

3️⃣ New Reranker Documentation
- New Training Overview, Loss Overview, API Reference docs
- 5 new, 1 refactored training examples docs pages
- 13 new, 6 refactored training scripts
- Migration guides (2.x -> 3.x, 3.x -> 4.x)

4️⃣ Blogpost
Alongside the release, I've written a blogpost where I finetune ModernBERT on a generic question-answer dataset. My finetunes easily outperform all general-purpose reranker models, even models 4x as big. Finetuning on your domain is definitely worth it: https://huggingface.co./blog/train-reranker

See the full release notes here: https://github.com/UKPLab/sentence-transformers/releases/v4.0.1
ZennyKennyΒ 
posted an update about 15 hours ago
view post
Post
761
Besides being the coolest named benchmark in the game, HellaSwag is an important measurement of Π·Π΄Ρ€Π°Π²Ρ‹ΠΉ ΡΠΌΡ‹ΡΠ»ΡŒ (or common sense) in LLMs.

- More on HellaSwag: https://github.com/rowanz/hellaswag

I spent the afternoon benchmarking YandexGPT Pro 4th Gen, one of the Russian tech giant's premier models.

- Yandex HF Org: https://huggingface.co./yandex
- More on Yandex models: https://yandex.cloud/ru/docs/foundation-models/concepts/yandexgpt/models

The eval notebook is available on GitHub and the resulting dataset is already on the HF Hub!

- Eval Notebook: https://github.com/kghamilton89/ai-explorer/blob/main/yandex-hellaswag/hellaswag-assess.ipynb
- Eval Dataset: ZennyKenny/yandexgptpro_4th_gen-hellaswag

And of course, everyone wants to see the results so have a look at the results in the context of other zero-shot experiments that I was able to find!
  • 2 replies
Β·
KeltezaaΒ 
posted an update about 17 hours ago
view post
Post
596
Is it just me or are the ZeroGPU not refreshing/restoring/regen...?
Last time I used my allocated ZeroGPU was over 4 hours ago and I have only recovered 70 seconds?

WTF..is going on? Correct me if I am wrong here but something is "OFF".
And I still feel as a Subscriber, the regen is way to slow.
Please Fix this for all of us.
  • 5 replies
Β·
Recently active users