Shetu Mohanto

shetumohanto

AI & ML interests

GenAI | MLOps | AI agent | Computer Vision

Recent Activity

Reacted to davidberenstein1957's post with 🔥 1 day ago

Introducing the Synthetic Data Generator, a user-friendly application that takes a no-code approach to creating custom datasets with Large Language Models (LLMs). The best part: A simple step-by-step process, making dataset creation a non-technical breeze, allowing anyone to create datasets and models in minutes and without any code. Blog: https://huggingface.co/blog/synthetic-data-generator Space: https://huggingface.co/spaces/argilla/synthetic-data-generator

Reacted to davidberenstein1957's post with ❤️ 1 day ago

Reacted to lewtun's post with 🔥 1 day ago

We outperform Llama 70B with Llama 3B on hard math by scaling test-time compute 🔥 How? By combining step-wise reward models with tree search algorithms :) We show that smol models can match or exceed the performance of their much larger siblings when given enough "time to think" We're open sourcing the full recipe and sharing a detailed blog post. In our blog post we cover: 📈 Compute-optimal scaling: How we implemented DeepMind's recipe to boost the mathematical capabilities of open models at test-time. 🎄 Diverse Verifier Tree Search (DVTS): An unpublished extension we developed to the verifier-guided tree search technique. This simple yet effective method improves diversity and delivers better performance, particularly at large test-time compute budgets. 🧭 Search and Learn: A lightweight toolkit for implementing search strategies with LLMs and built for speed with vLLM Here's the links: - Blog post: https://huggingface.co/spaces/HuggingFaceH4/blogpost-scaling-test-time-compute - Code: https://github.com/huggingface/search-and-learn Enjoy!

View all activity

Organizations

shetumohanto's activity

reacted to davidberenstein1957's post with 🔥❤️ 1 day ago

Post

2750

Introducing the Synthetic Data Generator, a user-friendly application that takes a no-code approach to creating custom datasets with Large Language Models (LLMs). The best part: A simple step-by-step process, making dataset creation a non-technical breeze, allowing anyone to create datasets and models in minutes and without any code.

Blog: https://huggingface.co/blog/synthetic-data-generator
Space: argilla/synthetic-data-generator

3 replies

reacted to lewtun's post with 🔥❤️ 1 day ago

Post

3636

We outperform Llama 70B with Llama 3B on hard math by scaling test-time compute 🔥

How? By combining step-wise reward models with tree search algorithms :)

We show that smol models can match or exceed the performance of their much larger siblings when given enough "time to think"

We're open sourcing the full recipe and sharing a detailed blog post.

In our blog post we cover:

📈 Compute-optimal scaling: How we implemented DeepMind's recipe to boost the mathematical capabilities of open models at test-time.

🎄 Diverse Verifier Tree Search (DVTS): An unpublished extension we developed to the verifier-guided tree search technique. This simple yet effective method improves diversity and delivers better performance, particularly at large test-time compute budgets.

🧭 Search and Learn: A lightweight toolkit for implementing search strategies with LLMs and built for speed with vLLM

Here's the links:

- Blog post: HuggingFaceH4/blogpost-scaling-test-time-compute

- Code: https://github.com/huggingface/search-and-learn

Enjoy!

2 replies

reacted to aaditya's post with ❤️ 1 day ago

Post

2768

Last Week in Medical AI: Top Research Papers/Models 🔥
🏅 (December 7 – December 14, 2024)

Medical LLM & Other Models
- PediaBench: Chinese Pediatric LLM
- Comprehensive pediatric dataset
- Advanced benchmarking platform
- Chinese healthcare innovation
- BiMediX: Bilingual Medical LLM
- Multilingual medical expertise
- Diverse medical knowledge integration
- Cross-cultural healthcare insights
- MMedPO: Vision-Language Medical LLM
- Clinical multimodal optimization
- Advanced medical image understanding
- Precision healthcare modeling

Frameworks and Methodologies
- TOP-Training: Medical Q&A Framework
- Hybrid RAG: Secure Medical Data Management
- Zero-Shot ATC Clinical Coding
- Chest X-Ray Diagnosis Architecture
- Medical Imaging AI Democratization

Benchmarks & Evaluations
- KorMedMCQA: Korean Healthcare Licensing Benchmark
- Large Language Model Medical Tasks
- Clinical T5 Model Performance Study
- Radiology Report Quality Assessment
- Genomic Analysis Benchmarking

Medical LLM Applications
- BRAD: Digital Biology Language Model
- TCM-FTP: Herbal Prescription Prediction
- LLaSA: Activity Analysis via Sensors
- Emergency Department Visit Predictions
- Neurodegenerative Disease AI Diagnosis
- Kidney Disease Explainable AI Model

Ethical AI & Privacy
- Privacy-Preserving LLM Mechanisms
- AI-Driven Digital Organism Modeling
- Biomedical Research Automation
- Multimodality in Medical Practice

Full thread in detail: https://x.com/OpenlifesciAI/status/1867999825721242101

3 replies

reacted to lewtun's post with ❤️ 1 day ago

Post

3636

We outperform Llama 70B with Llama 3B on hard math by scaling test-time compute 🔥

How? By combining step-wise reward models with tree search algorithms :)

We show that smol models can match or exceed the performance of their much larger siblings when given enough "time to think"

We're open sourcing the full recipe and sharing a detailed blog post.

In our blog post we cover:

📈 Compute-optimal scaling: How we implemented DeepMind's recipe to boost the mathematical capabilities of open models at test-time.

🎄 Diverse Verifier Tree Search (DVTS): An unpublished extension we developed to the verifier-guided tree search technique. This simple yet effective method improves diversity and delivers better performance, particularly at large test-time compute budgets.

🧭 Search and Learn: A lightweight toolkit for implementing search strategies with LLMs and built for speed with vLLM

Here's the links:

- Blog post: HuggingFaceH4/blogpost-scaling-test-time-compute

- Code: https://github.com/huggingface/search-and-learn

Enjoy!

2 replies

reacted to qq8933's post with 🚀 16 days ago

Post

3033

The first version of LLaMA-O1 has been uploaded to HF now!Here We Come!
Supervised:
SimpleBerry/LLaMA-O1-Supervised-1129
Base(Pretrain):
SimpleBerry/LLaMA-O1-Base-1127
Supervised Finetune Dataset:
SimpleBerry/OpenLongCoT-SFT
Pretraining Dataset:
SimpleBerry/OpenLongCoT-Pretrain-1202
RLHF is on the way! View our GitHub Repo:
https://github.com/SimpleBerry/LLaMA-O1
Our ongoing related researches:
Accessing GPT-4 level Mathematical Olympiad Solutions via Monte Carlo Tree Self-refine with LLaMa-3 8B (2406.07394)
LLaMA-Berry: Pairwise Optimization for O1-like Olympiad-Level Mathematical Reasoning (2410.02884)
Critic-V: VLM Critics Help Catch VLM Errors in Multimodal Reasoning (2411.18203)
@AdinaY @akhaliq @jwu323
------
GGUF:https://huggingface.co/Lyte/LLaMA-O1-Supervised-1129-Q4_K_M-GGUF
online Demo (CPU-only): SimpleBerry/LLaMA-O1-Supervised-1129-Demo

3 replies

reacted to sayakpaul's post with 🔥 16 days ago

Post

1460

Let 2024 be the year of video model fine-tunes!

Check it out here:
https://github.com/a-r-r-o-w/cogvideox-factory/tree/main/training/mochi-1

reacted to hexgrad's post with 🔥 17 days ago

Post

2847

self.brag(): Kokoro finally got 300 votes in Pendrokar/TTS-Spaces-Arena after @Pendrokar was kind enough to add it 3 weeks ago.
Discounting the small sample size of votes, I think it is safe to say that hexgrad/Kokoro-TTS is currently a top 3 model among the contenders in that Arena. This is notable because:
- At 82M params, Kokoro is one of the smaller models in the Arena
- MeloTTS has 52M params
- F5 TTS has 330M params
- XTTSv2 has 467M params

5 replies

reacted to merve's post with 👍 19 days ago

Post

2139

The authors of ColPali trained a retrieval model based on SmolVLM 🤠 vidore/colsmolvlm-alpha
TLDR;

- ColSmolVLM performs better than ColPali and DSE-Qwen2 on all English tasks

- ColSmolVLM is more memory efficient than ColQwen2 💗

reacted to andito's post with 🔥❤️ 19 days ago

Post

3208

Let's go! We are releasing SmolVLM, a smol 2B VLM built for on-device inference that outperforms all models at similar GPU RAM usage and tokens throughputs.

- SmolVLM generates tokens 7.5 to 16 times faster than Qwen2-VL! 🤯
- Other models at this size crash a laptop, but SmolVLM comfortably generates 17 tokens/sec on a macbook! 🚀
- SmolVLM can be fine-tuned on a Google collab! Or process millions of documents with a consumer GPU!
- SmolVLM even outperforms larger models in video benchmarks, despite not even being trained on videos!

Check out more!
Demo: HuggingFaceTB/SmolVLM
Blog: https://huggingface.co/blog/smolvlm
Model: HuggingFaceTB/SmolVLM-Instruct
Fine-tuning script: https://github.com/huggingface/smollm/blob/main/finetuning/Smol_VLM_FT.ipynb

reacted to openfree's post with ❤️ 19 days ago

Post

3191

Hackathon: 1-Minute Creative Innovation with AI
Total Prize: 20,000 USD(USDT)

"One-minute creation by AI Coding Autonomous Agent MOUSE-I"
Hosted by VIDraft | Organized by Korea AI Promotion Association (KAIPA)

🌟 Revolutionary Era of AI Coding
"Creating a web app in just one minute" - This is no longer just imagination, but reality. With the emergence of AI Coding Autonomous Agent MOUSE-I ("One-minute creation by AI Coding Autonomous Agent MOUSE-I"), we are witnessing a new era of software development.

🏆 Period & Prizes
Period: November 28 - December 23, 2024

Total Prize: 20,000 USD(USDT)

🏆
Top Rank: 10,000 USDT
Highest HuggingFace Trending Rank

❤️
Top Likes: 5,000 USDT
Most Likes

💫
Top Creative: 5,000 USDT
Most Innovative

🚀 Participation Process
1. Start with MOUSE-I
• Access https://VIDraft-mouse1.hf.space
• Notice VIDraft/Mouse-Hackathon
• Generate basic web app code in 1 minute
• Create unlimited content: games, dashboards, landing pages, utilities, etc.

2. Creative Development
• Free development based on MOUSE-I generated code
• Additional languages like Python can be used

3. Submission
• Public deployment on Hugging Face
• Register in Static mode
• Required in README.md:

short_description: "One-minute creation by AI Coding Autonomous Agent MOUSE-I"

📅 Key Dates
• Submission Deadline: December 23, 2024, midnight (NYC time)
• Winners Announcement: December 24, 2024

✨ Participant Benefits
• Full ownership and copyright of all creations
• Experience new paradigm of AI coding
• Multiple submissions allowed from the same account
• Contact: arxivgpt@gmail.com

"Give Yourself the Best Christmas Gift

reacted to as-cle-bert's post with 🔥 21 days ago

Post

1253

Hi HuggingFacers!🤗
I'm thrilled to introduce my latest project: 𝗦𝗲𝗻𝗧𝗿𝗘𝘃 (𝗦𝗲𝗻tence 𝗧𝗿ansformers 𝗘𝘃aluator), a python package that offers simple customizable evaluation for text retrieval accuracy and time performance of Sentence Transformers-compatible text embedders on PDF data!📊

Learn more in my LinkedIn post: https://www.linkedin.com/posts/astra-clelia-bertelli-583904297_python-embedders-semanticsearch-activity-7266754133557190656-j1e3

And on the GitHub repo: https://github.com/AstraBert/SenTrEv

Have fun!🍕

reacted to aaditya's post with ❤️ 24 days ago

Post

3357

Last Week in Medical AI: Top Research Papers/Models 🔥
(November 2 -November 9, 2024)

🏅 Medical AI Paper of the Week:
Exploring Large Language Models for Specialist-level Oncology Care

Medical LLM & Other Models:
- GSCo: Generalist-Specialist AI Collaboration
- PediatricsGPT: Chinese Pediatric Assistant
- MEG: Knowledge-Enhanced Medical QA
- AutoProteinEngine: Multimodal Protein LLM

Frameworks and Methodologies:
- BrainSegFounder: 3D Neuroimage Analysis
- PASSION: Sub-Saharan Dermatology Dataset
- SAM for Lung X-ray Segmentation
- Label Critic: Data-First Approach
- Medprompt Runtime Strategies

Medical LLM Applications:
- CataractBot: Patient Support System
- CheX-GPT: X-ray Report Enhancement
- CardioAI: Cancer Cardiotoxicity Monitor
- HealthQ: Healthcare Conversation Chain
- PRObot: Diabetic Retinopathy Assistant

Medical LLMs & Benchmarks:
- MediQ: Clinical Reasoning Benchmark
- Touchstone: Segmentation Evaluation
- Medical LLM Adaptation Progress
- Fine-Tuning Medical QA Strategies

AI in Healthcare Ethics:
- Healthcare Robotics with LLMs
- XAI in Clinical Practice
- Precision Rehabilitation Framework
- Multimodal AI Challenges

Now you can watch and listen to the latest Medical AI papers daily on our YouTube and Spotify channels as well!

- Full Thread: https://x.com/OpenlifesciAI/status/1855207141302473090
- YouTube: https://youtu.be/ad0uTnYuTo8
- Spotify: https://open.spotify.com/episode/6s39t1UJZk1i10szuXP2qN

reacted to aaditya's post with ❤️ about 2 months ago

Post

3245

Last Week in Medical AI: Top Research Papers/Models 🔥
🏅 (October 19-26, 2024)

🏅 Medical AI Paper of the Week:
Safety principles for medical summarization using generative AI by Google

Medical LLM & Other Models:
- BioMistral-NLU: Medical Vocab Understanding
- Bilingual Multimodal LLM for Biomedical Tasks
- Metabolic-Enhanced LLMs for Clinical Analysis
- Dermatology Foundation Model

Frameworks and Methodologies:
- Back-in-Time: Medical Deepfake Detection
- Hybrid GenAI for Crystal Design
- VISAGE: Video Synthesis for Surgery
- MoRE: Multi-Modal X-Ray/ECG Pretraining
- SleepCoT: Personalized Health via CoT

Medical LLM Applications:
- ONCOPILOT: CT Model for Tumors
- LMLPA: Linguistic Personality Assessment
- GenAI for Medical Training

Medical LLMs & Benchmarks:
- LLM Evaluation Through Explanations
- Contrastive Decoding for Medical LLM Hallucination

AI in Healthcare Ethics:
- Healthcare XAI Through Storytelling
- Clinical LLM Bias Analysis
- ReflecTool: Reflection-Aware Clinical Agents

Full Thread: https://x.com/OpenlifesciAI/status/1850202986053808441
Now you can watch and listen to the latest Medical AI papers daily on our YouTube and Spotify channels as well!

- 🎙️ Spotify: https://podcasters.spotify.com/pod/show/medicalai/episodes/Medical-AI-Weekly-Digest-From-Deepfake-Detection-to-Clinical-LLMs-Oct-19-26--Part-1-e2q6012

- YouTube: https://youtu.be/Wt5QOv1vk2U

reacted to aaditya's post with ❤️ about 2 months ago

Post

2743

Last Week in Medical AI: Top LLM Research Papers/Models 🔥
🏅 (October 12 - October 19, 2024)

Medical LLM & Other Models:
- OLAPH: Factual Biomedical LLM QA
- LLMD: Interpreting Longitudinal Medical Records
- LifeGPT: Generative Transformer for Cells
- MedCare: Decoupled Clinical LLM Alignment
- Y-Mol: Biomedical LLM for Drug Development

Frameworks and Methodologies:
- MedINST: Biomedical Instructions Meta Dataset
- Democratizing Medical LLMs via Language Experts
- MCQG-SRefine: Iterative Question Generation
- Adaptive Medical Language Agents
- MeNTi: Medical LLM with Nested Tools

Medical LLM Applications:
- AGENTiGraph: LLM Chatbots with Private Data
- MMed-RAG: Multimodal Medical RAG System
- Medical Graph RAG: Safe LLM via Retrieval
- MedAide: Multi-Agent Medical LLM Collaboration
- Synthetic Clinical Trial Generation

Medical LLMs & Benchmarks:
- WorldMedQA-V: Multimodal Medical LLM Dataset
- HEALTH-PARIKSHA: RAG Models Evaluation
- Synthetic Data for Medical Vision-Language

Now you can watch and listen to the latest Medical AI papers daily on our YouTube and Spotify channels as well!

- Youtube: https://youtu.be/LROOjWXUgvg?si=s-nNDOSD3BrsHYjQ
- Spotify : https://open.spotify.com/episode/12xeN2vnOTRdDrHbWqhV6I?si=bd7c8d9fee8049fd

1 reply

reacted to aaditya's post with ❤️👍 3 months ago

Post

2557

Last Week in Medical AI: Top Research Papers/Models
🏅(September 7 - September 14, 2024)

🏅 Medical AI Paper of the week
Chai-1 Foundation model molecular structure prediction

Medical LLMs & Benchmarks
- BrainWave: A Brain Signal Foundation Model
- DS-ViT: Vision Transformer for Alzheimer’s Diagnosis
- EyeCLIP: Visual–language model for ophthalmic
- Segment Anything Model for Tumor Segmentation
- MEDIC: Evaluating LLMs in Clinical Applications

Medical LLM Applications
- KARGEN: Radiology Report Generation LLMs
- DrugAgent: Explainable Drug Repurposing Agents
- Improving RAG in Medicine with Follow-up Questions

Frameworks and Methodologies
- Infrastructure for Automatic Cell Segmentation
- Data Alignment for Dermatology AI
- Diagnostic Reasoning in Natural Language
- Two-Stage Instruction Fine-tuning Approach for Med

AI in Healthcare Ethics
- Concerns and Choices of Using LLMs for Healthcare
- Understanding Fairness in Recommender Systems
- Towards Fairer Health Recommendations

Check the full thread: https://x.com/OpenlifesciAI/status/1832476252260712788

Thank you for your continued support and love for this series! Stay up-to-date with weekly updates on Medical LLMs, datasets, and top research papers by following @aaditya 🤗

liked a model 3 months ago

mattshumer/Reflection-Llama-3.1-70B

Text Generation • Updated Sep 24 • 1.05k • 1.71k