nerdyface (Nerdy Face)

m-ric

posted an update about 21 hours ago

Post

845

smolagents now support vLLM! 🥳

As one of the most popular local inference solutions, the community had been asking us to integrate vLLM: after a heavy refactoring of our LLM classes, we've just released smolagents 1.11.0, with a brand new VLLMModel class.

Go try it and tell us what you think!

https://github.com/huggingface/smolagents/blob/45b2c86857b7f7657daaa74e4d17d347e9e2c4a4/src/smolagents/models.py#L497

prithivMLmods

posted an update 2 days ago

Post

438

Hey Guys! One Small Announcement 🤗
Stranger Zone now accepts LoRA requests!

✍️Request : strangerzonehf/Request-LoRA [ or ] strangerzonehf/Request-LoRA#1

Page : https://huggingface.co/strangerzonehf

Describe the artistic properties by posting sample images or links to similar images in the request discussion. If the adapters you're asking for are truly creative and safe for work, I'll train and upload the LoRA to the Stranger Zone repo!

Thank you!

prithivMLmods

posted an update 4 days ago

Post

2392

Gemma-3-4B : Image and Video Inference 🖼️🎥

🧤Space: prithivMLmods/Gemma-3-Multimodal

@gemma3 : {Tag + Space_+ 'prompt'}
@video-infer : {Tag + Space_+ 'prompt'}

+ Gemma3-4B : google/gemma-3-4b-it
+ By default, it runs : prithivMLmods/Qwen2-VL-OCR-2B-Instruct

Gemma 3 Technical Report : https://storage.googleapis.com/deepmind-media/gemma/Gemma3Report.pdf

1 reply

·

thomwolf

posted an update 4 days ago

Post

2127

We've kept pushing our Open-R1 project, an open initiative to replicate and extend the techniques behind DeepSeek-R1.

And even we were mind-blown by the results we got with this latest model we're releasing: ⚡️OlympicCoder ( open-r1/OlympicCoder-7B and open-r1/OlympicCoder-32B)

It's beating Claude 3.7 on (competitive) programming –a domain Anthropic has been historically really strong at– and it's getting close to o1-mini/R1 on olympiad level coding with just 7B parameters!

And the best part is that we're open-sourcing all about its training dataset, the new IOI benchmark, and more in our Open-R1 progress report #3: https://huggingface.co/blog/open-r1/update-3

Datasets are are releasing:
- open-r1/codeforces
- open-r1/codeforces-cots
- open-r1/ioi
- open-r1/ioi-test-cases
- open-r1/ioi-sample-solutions
- open-r1/ioi-cots
- open-r1/ioi-2024-model-solutions

prithivMLmods

posted an update 5 days ago

Post

2738

Variable Demo for Two Image-to-Text-to-Text Multimodals 🌠

📜Space: prithivMLmods/Multimodal-OCR

By default, it will use:
prithivMLmods/Qwen2-VL-OCR-2B-Instruct or
prithivMLmods/Qwen2-VL-OCR2-2B-Instruct

To trigger Aya-Vision's 8B by @aya-vision , use the prompt:
CohereForAI/aya-vision-8b

m-ric

posted an update 6 days ago

Post

867

Our new Agentic leaderboard is now live!💥

If you ever asked which LLM is best for powering agents, we've just made a leaderboard that ranks them all! Built with @albertvillanova , this ranks LLMs powering a smolagents CodeAgent on subsets of various benchmarks. ✅

🏆 GPT-4.5 comes on top, even beating reasoning models like DeepSeek-R1 or o1. And Claude-3.7-Sonnet is a close second!

The leaderboard also allows you to show the scores of vanilla LLMs (without any agentic setup) on the same benchmarks: this shows the huge improvements brought by agentic setups. 💪

(Note that results will be added manually, so the leaderboard might not always have the latest LLMs)

1 reply

·

JingzeShi

posted an update 7 days ago

Post

4636

We distill a more accurate and concise dataset from DeepSeek R1, and also provide a distillation pipeline code repository.🤗

Dataset: SmallDoge/SmallThoughts
Code: https://github.com/SmallDoges/small-thoughts

Tonic

posted an update 9 days ago

Post

1047

🙋🏻‍♂️Hey there folks,

Did you know that you can use ModernBERT to detect model hallucinations ?

Check out the Demo : Tonic/hallucination-test

See here for Medical Context Demo : MultiTransformer/tonic-discharge-guard

check out the model from KRLabs : KRLabsOrg/lettucedect-large-modernbert-en-v1

and the library they kindly open sourced for it : https://github.com/KRLabsOrg/LettuceDetect

👆🏻if you like this topic please contribute code upstream 🚀

2 replies

·

taesiri

authored a paper 9 days ago

HoT: Highlighted Chain of Thought for Referencing Supporting Facts from Inputs

Paper • 2503.02003 • Published 13 days ago • 43

Tonic

posted an update 11 days ago

Post

660

Powered by KRLabsOrg/lettucedect-large-modernbert-en-v1 from KRLabsOrg.

Detect hallucinations in answers based on context and questions using ModernBERT with 8192-token context support!

### Model Details
- **Model Name**: [lettucedect-large-modernbert-en-v1]( KRLabsOrg/lettucedect-large-modernbert-en-v1)
- **Organization**: [KRLabsOrg](https://huggingface.co/KRLabsOrg)
- **Github**: [https://github.com/KRLabsOrg/LettuceDetect](https://github.com/KRLabsOrg/LettuceDetect)
- **Architecture**: ModernBERT (Large) with extended context support up to 8192 tokens
- **Task**: Token Classification / Hallucination Detection
- **Training Dataset**: [RagTruth]( wandb/RAGTruth-processed)
- **Language**: English
- **Capabilities**: Detects hallucinated spans in answers, provides confidence scores, and calculates average confidence across detected spans.

LettuceDetect excels at processing long documents to determine if an answer aligns with the provided context, making it a powerful tool for ensuring factual accuracy.

prithivMLmods

posted an update 11 days ago

Post

4922

SigLIP2 Image Classification 🧤

> https://huggingface.co/blog/prithivMLmods/siglip2-finetune-image-classification

prithivMLmods

posted an update 19 days ago

Post

5855

Dropping some of the custom fine-tunes based on SigLIP2,
with a single/multi label classification problem type! 🌀🧤

- AI vs Deepfake vs Real : prithivMLmods/AI-vs-Deepfake-vs-Real-Siglip2
- Deepfake Detect : prithivMLmods/Deepfake-Detect-Siglip2
- Fire Detection : prithivMLmods/Fire-Detection-Siglip2
- Deepfake Quality Assess : prithivMLmods/Deepfake-Quality-Assess-Siglip2
- Guard Against Unsafe Content : prithivMLmods/Guard-Against-Unsafe-Content-Siglip2

🌠Collection : prithivMLmods/siglip2-custom-67bcdb2de8fe96b99fb4e19e

m-ric

posted an update 20 days ago

Post

4741

We now have a Deep Research for academia: SurveyX automatically writes academic surveys nearly indistinguishable from human-written ones 🔥

Researchers from Beijing and Shanghai just published the first application of a deep research system to academia: their algorithm, given a question, can give you a survey of all papers on the subject.

To make a research survey, you generally follow two steps, preparation (collect and organize papers) and writing (outline creation, writing, polishing). Researchers followed the same two steps and automated them.

🎯 For the preparation part, a key part is find all the important references on the given subject.
Researchers first cast a wide net of all relevant papers. But then finding the really important ones is like distilling knowledge from a haystack of information. To solve this challenge, they built an “AttributeTree” object that structures key information from citations. Ablating these AttributeTrees significantly decreased structure and synthesis scores, so they were really useful!

📝 For the writing part, key was to get a synthesis that's both short and true. This is not easy to get with LLMs! So they used methods like LLM-based deduplication to shorten the too verbose listings made by LLMs, and RAG to grab original quotes instead of made-up ones.

As a result, their system outperforms previous approaches by far!

As assessed by LLM-judges, the quality score os SurveyX even approaches this of human experts, with 4.59/5 vs 4.75/5 🏆

I advise you to read the paper, it's a great overview of the kind of assistants that we'll get in the short future! 👉 SurveyX: Academic Survey Automation via Large Language Models (2502.14776)
Their website shows examples of generated surveys 👉 http://www.surveyx.cn/

prithivMLmods

posted an update 22 days ago

Post

5829

It's really interesting about the deployment of a new state of matter in Majorana 1: the world’s first quantum processor powered by topological qubits. If you missed this news this week, here are some links for you:

🅱️Topological qubit arrays: https://arxiv.org/pdf/2502.12252

⚛️ Quantum Blog: https://azure.microsoft.com/en-us/blog/quantum/2025/02/19/microsoft-unveils-majorana-1-the-worlds-first-quantum-processor-powered-by-topological-qubits/

📖 Read the story: https://news.microsoft.com/source/features/innovation/microsofts-majorana-1-chip-carves-new-path-for-quantum-computing/

📝 Majorana 1 Intro: https://youtu.be/Q4xCR20Dh1E?si=Z51DbEYnZFp_88Xp

🌀The Path to a Million Qubits: https://youtu.be/wSHmygPQukQ?si=TS80EhI62oWiMSHK

3 replies

·

JingzeShi

posted an update 23 days ago

Post

2948

🤗Welcome to the Doge Edge Device Small language Model.

SmallDoge/Doge-160M-Instruct

prithivMLmods

posted an update 26 days ago

Post

3922

Dino: The Minimalist Multipurpose Chat System 🌠
Agent-Dino : prithivMLmods/Agent-Dino
Github: https://github.com/PRITHIVSAKTHIUR/Agent-Dino

By default, it performs the following tasks:
{Text-to-Text Generation}, {Image-Text-Text Generation}
@image: Generates an image using Stable Diffusion xL.
@3d: Generates a 3D mesh.
@web: Web search agents.
@rAgent: Initiates a reasoning chain using Llama mode for coding explanations.
@tts1-♀, @tts2-♂: Voice generation (Female and Male voices).
@yolo : Object Detection

m-ric

posted an update 26 days ago

Post

3039

Less is More for Reasoning (LIMO): a 32B model fine-tuned with 817 examples can beat o1-preview on math reasoning! 🤯

Do we really need o1's huge RL procedure to see reasoning emerge? It seems not.
Researchers from Shanghai Jiaotong University just demonstrated that carefully selected examples can boost math performance in large language models using SFT —no huge datasets or RL procedures needed.

Their procedure allows Qwen2.5-32B-Instruct to jump from 6.5% to 57% on AIME and from 59% to 95% on MATH, while using only 1% of the data in previous approaches.

⚡ The Less-is-More Reasoning Hypothesis:
‣ Minimal but precise examples that showcase optimal reasoning patterns matter more than sheer quantity
‣ Pre-training knowledge plus sufficient computational resources at inference levels up math skills

➡️ Core techniques:
‣ High-quality reasoning chains with self-verification steps
‣ 817 handpicked problems that encourage deeper reasoning
‣ Enough inference-time computation to allow extended reasoning

💪 Efficiency gains:
‣ Only 817 examples instead of 100k+
‣ 40.5% absolute improvement across 10 diverse benchmarks, outperforming models trained on 100x more data

This really challenges the notion that SFT leads to memorization rather than generalization! And opens up reasoning to GPU-poor researchers 🚀

Read the full paper here 👉 LIMO: Less is More for Reasoning (2502.03387)

taesiri

authored a paper 26 days ago

ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models

Paper • 2502.09696 • Published about 1 month ago • 39

prithivMLmods

posted an update 28 days ago

Post

4493

The last week of Impression Craft Arts and sketches from strangerzonehf🎨🧑🏻‍🎨

- Collection : strangerzonehf/Flux-Ultimate-LoRA-Collection

Adapters:
+ Ld-Art : strangerzonehf/Ld-Art
+ Animeopix-Flux : strangerzonehf/Animeopix-Flux
+ Flux-Super-Paint-LoRA : strangerzonehf/Flux-Super-Paint-LoRA
+ CinematicShot-Pics-Flux : strangerzonehf/cinematicShot-Pics-Flux
+ Oil-Wall-Art-Flux : strangerzonehf/Oil-Wall-Art-Flux
+ Pixelo-Flux : strangerzonehf/Pixelo-Flux
+ Abstract-Shattered : strangerzonehf/Abstract-Shattered
+ Neon-Impressionism-Flux : strangerzonehf/Neon-Impressionism-Flux
+ NewG-Art : strangerzonehf/NewG-Art

🪧Demo : prithivMLmods/FLUX-LoRA-DLC
🤗Page : https://huggingface.co/strangerzonehf

m-ric

posted an update 30 days ago

Post

2914

𝗚𝗿𝗲𝗮𝘁 𝗳𝗲𝗮𝘁𝘂𝗿𝗲 𝗮𝗹𝗲𝗿𝘁: you can now share agents to the Hub! 🥳🥳

And any agent pushed to Hub get a cool Space interface to directly chat with it.

This was a real technical challenge: for instance, serializing tools to export them meant that you needed to get all the source code for a tool, verify that it was standalone (not relying on external variables), and gathering all the packages required to make it run.

Go try it out! 👉 https://github.com/huggingface/smolagents

2 replies

·

Nerdy Face

AI & ML interests

Recent Activity

nerdyface's activity

HoT: Highlighted Chain of Thought for Referencing Supporting Facts from Inputs

ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models

AI & ML interests

Recent Activity

Team members 266

nerdyface's activity