SelmaNajih001 (Selma Najih)

reacted to sergiopaniego's post with 🚀 26 days ago

Post

2842

Meet OpenEnv 👋, an open ecosystem of environments for intelligent agents. Build, share, and test agents safely and consistently.

Ideal for training with TRL (we include examples🤓), deployment, and community collaboration via the HF Hub

Blog: https://huggingface.co/blog/openenv
Hub for Environments:

openenv
OpenEnv repo: https://github.com/meta-pytorch/OpenEnv
Try it out using TRL: https://huggingface.co/docs/trl/main/en/openenv

1 reply

·

posted an update 27 days ago

Post

2802

How Financial News Can Be Used to Train Good Financial Models 📰
Numbers tell you what happened, but news tells you why.
I’ve written an article explaining how news can be used to train AI models for sentiment analysis and better forecasting. Hope you find it interesting!

Read it here: https://huggingface.co/blog/SelmaNajih001/llms-applied-to-finance

I would love to read your opinions! I’m open to suggestions on how to improve the methodology and the training

1 reply

·

reacted to tomaarsen's post with 🚀 28 days ago

Post

3801

🤗 Sentence Transformers is joining Hugging Face! 🤗 This formalizes the existing maintenance structure, as I've personally led the project for the past two years on behalf of Hugging Face! Details:

Today, the Ubiquitous Knowledge Processing (UKP) Lab is transferring the project to Hugging Face. Sentence Transformers will remain a community-driven, open-source project, with the same open-source license (Apache 2.0) as before. Contributions from researchers, developers, and enthusiasts are welcome and encouraged. The project will continue to prioritize transparency, collaboration, and broad accessibility.

Read our full announcement for more details and quotes from UKP and Hugging Face leadership: https://huggingface.co/blog/sentence-transformers-joins-hf

We see an increasing wish from companies to move from large LLM APIs to local models for better control and privacy, reflected in the library's growth: in just the last 30 days, Sentence Transformer models have been downloaded >270 million times, second only to transformers.

I would like to thank the UKP Lab, and especially Nils Reimers and Iryna Gurevych, both for their dedication to the project and for their trust in myself, both now and two years ago. Back then, neither of you knew me well, yet you trusted me to take the project to new heights. That choice ended up being very valuable for the embedding & Information Retrieval community, and I think this choice of granting Hugging Face stewardship will be similarly successful.

I'm very excited about the future of the project, and for the world of embeddings and retrieval at large!

1 reply

·

posted an update 28 days ago

Post

3010

Which is the best model to use as a signal for investment?
Here who is gaining the most:
SelmaNajih001/InvestmentStrategyBasedOnSentiment

The Space uses titles from this dataset:
📊 SelmaNajih001/Cnbc_MultiCompany

Given a news title, it calculates a sentiment score : if the score crosses a certain threshold, the strategy decides to buy or sell.
Each trade lasts one day, and the strategy then computes the daily return.
For Tesla the best model seems to be the regression 👀
Just a quick note: the model uses the closing price as the buy price, meaning it already reflects the impact of the news.

reacted to merve's post with 🚀 29 days ago

Post

5808

deepseek-ai/DeepSeek-OCR is out! 🔥 my take ⤵️
> pretty insane it can parse and re-render charts in HTML
> it uses CLIP and SAM features concatenated, so better grounding
> very efficient per vision tokens/performance ratio
> covers 100 languages

3 replies

·

reacted to appvoid's post with 👍 29 days ago

Post

4075

today is going to be a great day for small models, are you ready?

3 replies

·

reacted to prithivMLmods's post with 🤗 29 days ago

Post

2275

Let’s have the comparison again with Multimodal OCR3:

nanonets/Nanonets-OCR2-3B vs allenai/olmOCR-2-7B-1025 vs rednote-hilab/dots.ocr vs datalab-to/chandra

Try it here @ prithivMLmods/Multimodal-OCR3

Collection: prithivMLmods/multimodal-implementations-67c9982ea04b39f0608badb0

reacted to umarbutler's post with 👍👍👍 about 1 month ago

Post

2938

I'm excited to announce the release of Kanon 2 Embedder, the world's best legal embedding model, ranked first on the Massive Legal Embedding Benchmark 🎉

This model is the product of quite literally months of painstaking work alongside @abdurrahmanbutler collecting, cleaning, and processing terabytes of data as well as coming up with novel improvements to the standard embedder training recipe to push the limits of what's possible.

Kanon 2 Embedder is my most advanced model to date. On MLEB, it benchmarks as 9% more accurate than OpenAI's best embedding model and 30% faster.

Even when truncated from 1,792 to 768 dimensions, Kanon 2 Embedder continues to hold the number one spot on MLEB.

Importantly, Kanon 2 Embedder is also privacy and security friendly — unlike Voyage, Cohere and Jina, none of your data is used to train our models by default.

Kanon 2 Embedder can also be self-hosted for enterprises with heightened security or reliability requirements.

You can read the full announcement on our blog to learn how we did it and how you can get started using Kanon 2 Embedder to embed your own legal documents: https://isaacus.com/blog/introducing-kanon-2-embedder

2 replies

·

reacted to Kseniase's post with 👍 about 1 month ago

Post

4027

5 Lectures and keynotes defining AI right now

If you want to understand the multifaceted AI landscape in 2025 and see where the field is heading – start with (or revisit) these legendary talks. They can help you capture what’s happening in AI from multiple angles:

1. Andrej Karpathy: Software Is Changing (Again) → https://www.youtube.com/watch?v=LCEmiRjPEtQ
Unveils Software 3.0 – a paradigm where LLMs are the new computers, programmed with prompts instead of code. The key: developers must now master coding, training, and prompting as AI becomes the heart of software building

2. Richard Sutton, The OaK Architecture: A Vision of SuperIntelligence from Experience → https://www.youtube.com/watch?v=gEbbGyNkR2U
Unveils the OaK (Options and Knowledge) architecture – a model-based RL framework for continual intelligence, where every component learns, meta-learns & builds hierarchical abstractions

3. GTC March 2025 Keynote with NVIDIA CEO Jensen Huang → https://www.youtube.com/watch?v=_waPvOwL9Z8
Dives into the accelerated computing and the importance of Physical AI. From the Blackwell GPU architecture & AI factories to breakthroughs in agentic AI & robotics, Jensen Huang explains how NVIDIA aims to power every layer of the AI ecosystem

4. Yann LeCun "Mathematical Obstacles on the Way to Human-Level AI" → https://www.youtube.com/watch?v=ETZfkkv6V7
Yann LeCun always argues we need a new path to machines that reason about the world – not LLMs or RL. So this lecture is about self-supervised systems with world models, planning, memory and energy-based learning

5. Andrew Ng: State of AI Agents → https://www.youtube.com/watch?v=4pYzYmSdSH4
Highlights one of the most pressing topics of 2025 – agents, explaining why most effective AI agents rely on simple, linear workflows built from modular “Lego-brick” tasks + what predicts AI startup success in the new agent era

Subscribe to the Turing Post: https://www.turingpost.com/subscribe –your shortcut to deep, clear AI analysis

posted an update about 1 month ago

Post

671

How Financial News Can Be Used to Train Good Financial Models 📰
Numbers tell you what happened, but news tells you why.
I’ve written an article explaining how news can be used to train AI models for sentiment analysis and better forecasting. Hope you find it interesting!

Read it here: https://huggingface.co/blog/SelmaNajih001/llms-applied-to-finance

I would love to read your opinions! I’m open to suggestions on how to improve the methodology and the training

1 reply

·

reacted to kanaria007's post with 👀 about 1 month ago

Post

782

✅ New Article: *Structured Intelligence — Minimal Formalization*

Title:
📐 Structured Intelligence: Minimal Formalization of Intelligence
🔗 https://huggingface.co/blog/kanaria007/minimal-formalization-of-intelligence

---

Summary:
After cross-domain insights, *PoC* Series(SIC, Cosmic Exploration, etc), Reproducing Genius Series, Cosmic Intelligence Model, and Human Observation Series, we now move from narrative to *formal definition*.
This article presents a *minimal, implementation-agnostic spec*: intelligence defined not by algorithms or benchmarks, but by *invariants and interfaces* that any intelligent system must satisfy.

> Don’t ask *what algorithm it is*.
> Ask *which invariants it keeps, and which interfaces it honors*.

---

Why It Matters:
• Gives researchers and builders a *shared contract* for intelligence (human, AI, or institutional)
• Bakes in *safety and reversibility* (no opaque, irreversible reasoning qualifies)
• Enables *interoperability* across models by auditing structure instead of style

---

What’s Inside:
• Core Invariants (MUST): OBS (observation), ETH (ethics-trace & rollback), MEM (append-only history), ID (origin distinction), EVAL (high-risk evaluation)
• Standard Interfaces (Minimal): Problem-Readiness, Jump-Call (I/O), Observation-Evaluation, Ethics/Rollback hooks
• Conformance levels: SI-L0 / SI-L1 / SI-L2 (declared → logged → replayable)
• Falsifiability clause: clear failure modes that void an SI-intelligence claim

---

📖 *Formalization Series — Article 0 (Minimal Spec)*
This is the *smallest working definition*: enough to test, teach, and build on.

---

*Next: *SI Core Spec v0.1 — Essentials (Implementation Profile)*
Next entry is the *non-divergent Essentials profile* of the SI Core Spec — a concise, implementer-oriented subset for immediate adoption.

> From minimal formalization to implementable rules,
> *this profile lets you ship while the full spec remains the source of truth.*

replied to ZennyKenny's post about 1 month ago

Same for me.
I've lost like half of my followers

reacted to ZennyKenny's post with 👍 about 1 month ago

Post

2167

Did Hugging Face just ban hammer a bunch of bot accounts or am I just so uninteresting that 30% of my subs dropped me overnight?

😬 Wait, don't answer that.

2 replies

·

reacted to kanaria007's post with 👀 about 1 month ago

Post

2465

✅ New Article: *Humor as Structured Protocol*

Title:
🎭 Humor as Structured Protocol: Joke-Protocols as Emotion Regulation and AGI Design Resource
🔗 https://huggingface.co/blog/kanaria007/humor-as-structured-protocol

---

Summary:
Humor isn’t a distraction — it’s a *protocol*.
By framing paradox as *benign*, humor vents overload, resets attention, and enables safe re-entry to difficult topics.
In Structured Intelligence terms, jokes are *bounded anomalies* that discharge tension without breaking identity or trust.

> Laughter is relief.
> *Humor is the design that makes relief safe.*

---

Why It Matters:
• Turns “comic timing” into *recoverable state transitions* (no denial, no collapse)
• Gives teams and products a *de-escalation primitive* that preserves dignity
• Informs *AI/UX safety*: sandboxed incongruity, ethical gates, clear exit paths

---

What’s Inside:
• The Humor Protocol: trigger → incongruity → benign boundary → release → re-entry
• Patterns: irony, self-deprecation, reparative humor vs. status-aggression
• Safeguards: *parse-guard* (no harm payloads), *ethics-interface* (auditable limits), *reflexia* (post-joke repair)
• Metrics: relief half-life, re-entry latency, consent windows, social sync gain
• Applications: conflict mediation, teaching hard topics, resilient AI dialogue

---

📖 *Human Observation Series — Article 10*
This entry generalizes earlier “laughter as recovery” into a full *protocol*: how to design humor that heals rather than harms.

reacted to s3nh's post with 🔥 about 1 month ago

Post

4075

Just tried to create an educational assistant for younger people who can struggle with visualsation of 'what is this sorcery all about'.
Its first step of my spare time projects, sft on Qwen3-8B,

EduHelper is a child-friendly tutoring assistant fine-tuned from the Qwen3-8B base model using parameter-efficient fine-tuning (PEFT) with LoRA on the ajibawa-2023/Education-Young-Children dataset.

s3nh/EduHelp-8B

Glad to share my work, have a wonderful day!

2 replies

·

reacted to ronantakizawa's post with 👀 about 1 month ago

Post

3430

Released an AWQ quantized version of BosonAI’s Higgs-Llama-3-70B model! 🎉
The Higgs-Llama-3-70B is an LLM specialized in role-playing, useful for game characters.

Using an NVIDIA B200 GPU, I was able to compress the huge 140GB model into 37GB while keeping minimal perplexity 👍

ronantakizawa/higgs-llama-3-70b-awq

reacted to lbourdois's post with 👀 about 1 month ago

Post

1126

New blog post analyzing the top 50 entities with the most downloaded models on @huggingface 🤗!

https://huggingface.co/blog/lbourdois/huggingface-models-stats

The purpose here is to get an idea of the profile of the models with the greatest impact in open source (we are not interested in closed models here!).

32 figures + data

Enjoy 🤗

reacted to prithivMLmods's post with 👍 about 1 month ago

Post

3364

The demo of Qwen3-VL-30B-A3B-Instruct, the next-generation and powerful vision-language model in the Qwen series, delivers comprehensive upgrades across the board — including superior text understanding and generation, deeper visual perception and reasoning, extended context length, enhanced spatial and video dynamics comprehension, and stronger agent interaction capabilities. 🤗🔥

⚡ Space / App: prithivMLmods/Qwen3-VL-HF-Demo

The model’s demo supports a wide range of tasks, including;
Image Inference, Video Inference, PDF Inference, Image Captioning (VLA), GIF Inference.

⚡ Collection: prithivMLmods/multimodal-implementations-67c9982ea04b39f0608badb0

Thanks for granting the blazing-fast Zero GPU access, @merve 🙏

⚡ Other Pages

> Github: https://github.com/prithivsakthiur/qwen3-vl-hf-demo
> Multimodal VLMs July'25 : prithivMLmods/multimodal-vlms-until-july25-688312e6b840e1e156f13027
> VL caption — < Sep 15 ’25 : prithivMLmods/vl-caption-sep-15-25-68c7f6d737985c63c13e2391
> Multimodal VLMs - Aug'25 : prithivMLmods/multimodal-vlms-aug25-68a56aac39fe8084f3c168bd

To know more about it, visit the app page or the respective model page!!

Selma Najih PRO

AI & ML interests

Recent Activity

Organizations

Selma Najih PRO

AI & ML interests

Recent Activity

Organizations

SelmaNajih001's activity