replied to their post 2 days ago

Sir, basically I want to create a generative AI university helpdesk chatbot, and for this, I have created datasets myself and also fine-tuned models, but I am not getting satisfactory results. Sir, if you have time, could you please check my datasets in my profile and help me understand how I can improve my dataset and work on it so that my task gets completed? I would be very grateful to you.

I would enhance your dataset to use multi turn conversations if you can at all for llama2 you could do something like this:

<s>[INST] Is the BS Physics program a part-time or full-time course? [/INST] The BS Physics program is a full-time undergraduate program that requires regular on-campus attendance. </s><s>[INST] How many units per semester? [/INST] A typical semester load consists of 15-18 units. </s>

hope this helps! Again, please reach out to me on discord here: takarajordan_82155

replied to s3nh's post 15 days ago

gimme an invite! :D

reacted to s3nh's post with ❤️ 15 days ago

Post

1732

Welcome back,

Small Language Models Enthusiasts and GPU Poor oss enjoyers lets connect.
Just created an organization which main target is to have fun with smaller models tuneable on consumer range GPUs, feel free to join and lets have some fun, much love ;3

https://huggingface.co/SmolTuners

3 replies

·

replied to merve's post 15 days ago

Amazing work

reacted to merve's post with 🚀 15 days ago

Post

2722

Aya by Cohere For AI can now see! 👀

C4AI community has built Maya 8B, a new open-source multilingual VLM built on SigLIP and Aya 8B 🌱 works on 8 languages! 🗣️

The authors extend Llava dataset using Aya's translation capabilities with 558k examples!
ry it here kkr5155/maya_demo

Dataset maya-multimodal/pretrain

Model maya-multimodal/maya 👏
kudos @nahidalam and team

1 reply

·

reacted to merve's post with 🚀 15 days ago

Post

3150

Apollo is a new family of open-source video language models by Meta, where 3B model outperforms most 7B models and 7B outperforms most 30B models 🧶

✨ the models come in 1.5B https://huggingface.co/Apollo-LMMs/Apollo-1_5B-t32, 3B https://huggingface.co/Apollo-LMMs/Apollo-3B-t32 and 7B https://huggingface.co/Apollo-LMMs/Apollo-7B-t32 with A2.0 license, based on Qwen1.5 & Qwen2
✨ the authors also release a benchmark dataset https://huggingface.co/spaces/Apollo-LMMs/ApolloBench

The paper has a lot of experiments (they trained 84 models!) about what makes the video LMs work ⏯️

Try the demo for best setup here https://huggingface.co/spaces/Apollo-LMMs/Apollo-3B
they evaluate sampling strategies, scaling laws for models and datasets, video representation and more!
> The authors find out that whatever design decision was applied to small models also scale properly when the model and dataset are scaled 📈 scaling dataset has diminishing returns for smaller models
> They evaluate frame sampling strategies, and find that FPS sampling is better than uniform sampling, and they find 8-32 tokens per frame optimal
> They also compare image encoders, they try a variation of models from shape optimized SigLIP to DINOv2
they find google/siglip-so400m-patch14-384 to be most powerful 🔥
> they also compare freezing different parts of models, training all stages with some frozen parts give the best yield

They eventually release three models, where Apollo-3B outperforms most 7B models and Apollo 7B outperforms 30B models 🔥

6 replies

·

replied to sayakpaul's post 15 days ago

you guys are amazing!

reacted to sayakpaul's post with 🚀 15 days ago

Post

1697

In the past seven days, the Diffusers team has shipped:

1. Two new video models
2. One new image model
3. Two new quantization backends
4. Three new fine-tuning scripts
5. Multiple fixes and library QoL improvements

Coffee on me if someone can guess 1 - 4 correctly.

1 reply

·

reacted to lorraine2's post with 🚀 15 days ago

Post

1986

🦙New NVIDIA paper: LLaMA-Mesh 🦙

We enable large language models to generate and understand 3D meshes by representing them as text and fine-tuning. This unifies the 3D and text modalities in a single model and preserves language abilities, unlocking conversational 3D creation with mesh understanding.

🔎 Project Page: https://research.nvidia.com/labs/toronto-ai/LLaMA-Mesh/
🕹️ Interactive Demo: Zhengyi/LLaMA-Mesh (courtesy of HuggingFace and Gradio)
📖 Full Paper: https://arxiv.org/abs/2411.09595
👨‍💻Code: https://github.com/nv-tlabs/LLaMa-Mesh
💾 Model Checkpoint: Zhengyi/LLaMA-Mesh
🧩 Blender Addon: https://github.com/huggingface/meshgen (courtesy of Dylan Ebert)
🎥 5-min Overview Video: https://youtu.be/eZNazN-1lPo?si=-idQa5aaceVw0Bbj (courtesy of AI Papers Academy)

reacted to DualityAI-RebekahBogdanoff's post with ❤️🔥 15 days ago

Post

1953

Training YOLO with Synthetic Data from Duality AI's Falcon Simulation Software 🎮📊
Hello again! 👋 Duality.ai has released a second Google Colab and tutorial for training a YOLOv8 model using synthetic data from our Falcon simulation software!

https://falcon.duality.ai/secure/documentation/see-synth-work-no-specs?sidebarMode=learn#download-the-colab-notebook

Train using synthetic images of a soup can twin this time, and see it work on real-world images. 🥫🍜
The tutorial also walks you through how to add your own twin from our FalconCloud library, and our goal is to equip people like you to be able to create your own data for your own projects.

You'll have to create a free account to access the files, but once you do, you'll have access to not only this colab file, but also all of our lessons and our digital twin library. 🎓

Instructions for creating the synthetic data accessed by the colab notebook can be found here: https://falcon.duality.ai/secure/documentation/ex2-objdetection-newtwin?sidebarMode=learn

This method is a game-changer for cost-effective, scalable, and customizable datasets in computer vision.

Why Synthetic Data?🤔
- Precise Annotations: Get bounding boxes, segmentation masks, and more without manual effort.
- Customizable Scenarios: Get comprehensive data and cover all corner cases by simulating diverse conditions like lighting, weather, visual occlusions, and more.

What’s in the Notebook?📓
- Training & Evaluation: Train YOLOv8 with synthetic data and test its performance on real-world samples.

Let’s Discuss!💬
Check out our discord to see how people are using the Falcon simulation software to develop strong datasets and train robust models. https://discord.com/invite/dualityfalconcommunity

2 replies

·

reacted to prithivMLmods's post with ❤️ 15 days ago

Post

3214

🎄 Here Before - Xmas🎅✨

🧑🏻‍🎄Models
+ [ Xmas 2D Illustration ] : strangerzonehf/Flux-Xmas-Illustration-LoRA
+ [ Xmas 3D Art ] : strangerzonehf/Flux-Xmas-3D-LoRA
+ [ Xmas Chocolate ] : strangerzonehf/Flux-Xmas-Chocolate-LoRA
+ [ Xmas Isometric Kit ] : strangerzonehf/Flux-Xmas-Isometric-Kit-LoRA
+ [ Xmas Realpix ] : strangerzonehf/Flux-Xmas-Realpix-LoRA
+ [ Xmas Anime ] : strangerzonehf/Flux-Anime-Xmas-LoRA

❄️Collections
+ [ Xmas Art ] : strangerzonehf/christmas-pack-6758b199487adafaddb68f82
+ [ Stranger Zone Collection ] : prithivMLmods/stranger-zone-collections-org-6737118adcf2cb40d66d0c7e

🥶Page
+ [ Stranger Zone ] : https://huggingface.co/strangerzonehf

.
.
.
@prithivMLmods 🤗

reacted to davidberenstein1957's post with 🔥 15 days ago

Post

4158

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

4 replies

·

reacted to cutechicken's post with ❤️ 15 days ago

Post

2851

🚀 RAGOndevice: High-Performance Local AI Document Analysis Assistant
💫 Core Value
RAGOndevice is a high-performance AI system running locally without cloud dependency. Using CohereForAI's optimized 7B model, it enables professional-grade document analysis on standard PCs. ✨
🌟 Ondevice AI Advantages
1. 🔋 Efficient Resource Utilization

🎯 Optimized 7B Model: Runs on standard PCs
⚡ Local Processing: Instant response without cloud
💻 Low-Spec Compatible: Performs well on regular GPUs
🔄 Optimized Memory: Ensures stable operation

2. 🛡️ Data Security & Cost Efficiency

🔒 Complete Privacy: No external data transmission
🌐 Offline Operation: No internet required
💰 No Subscription: One-time installation
⚙️ Resource Optimization: Uses existing hardware

🎮 Key Features
1. 📊 Powerful Document Analysis

📁 Multi-Format Support: TXT, CSV, PDF, Parquet
🧠 Intelligent Analysis: Automatic structure recognition
👁️ OCR Support: Advanced PDF text extraction
💬 Real-time Chat: Natural language interaction

2. 🔍 Local RAG System

🎯 Efficient Search: TF-IDF based local search
🧩 Context Understanding: Accurate information retrieval
📚 Wikipedia Integration: Rich background knowledge

🎯 Use Cases

🏢 Enterprise: Secure confidential document processing
🔬 Personal Research: Private data analysis
📚 Education: Personal learning material analysis
💻 Development: Local codebase analysis

⭐ Differentiators

🏃‍♂️ Independent Operation: Zero cloud dependency
⚡ Instant Response: No network latency
🔐 Complete Security: Full data control
💎 Cost Efficiency: No ongoing costs

🔮 Future Plans

🚀 Enhanced model optimization
📚 Local knowledge base expansion
⚡ Hardware optimization
📁 Extended file support

🌟 RAGOndevice democratizes high-performance AI, providing the optimal local AI solution for security-sensitive environments. 🚀

🔥 Power of Local AI: Experience enterprise-grade AI capabilities right on your device!

VIDraft/RAGOndevice

reacted to lewtun's post with 🔥🚀 15 days ago

Post

6620

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 their post with 🚀 15 days ago

Post

1112

I made an RSS feed for HuggingFace Daily Papers!! 🤗

Just Subscribe here: https://papers.takara.ai/api/feed

It updates every 24 hours, completely written as a serverless go script with a Redis cache (to avoid hitting HF all the time).

I'm open sourcing the code, you can check out my repo and deploy it on Vercel extremely easily!
https://github.com/404missinglink/HF-Daily-Papers-Feeds

thanks to @John6666 @p3nGu1nZz for your early support

replied to their post 15 days ago

Thanks Clem!!

replied to their post 15 days ago

I preprocessed this into ChatML format to train the model takarajordan/WorldScenario-3.2B_GGUF and I used Unsloth to finetune it!

If you want more help join the HuggingFace discord, I'm always in there.

reacted to prithivMLmods's post with 🤗 16 days ago

Post

3214

🎄 Here Before - Xmas🎅✨

🧑🏻‍🎄Models
+ [ Xmas 2D Illustration ] : strangerzonehf/Flux-Xmas-Illustration-LoRA
+ [ Xmas 3D Art ] : strangerzonehf/Flux-Xmas-3D-LoRA
+ [ Xmas Chocolate ] : strangerzonehf/Flux-Xmas-Chocolate-LoRA
+ [ Xmas Isometric Kit ] : strangerzonehf/Flux-Xmas-Isometric-Kit-LoRA
+ [ Xmas Realpix ] : strangerzonehf/Flux-Xmas-Realpix-LoRA
+ [ Xmas Anime ] : strangerzonehf/Flux-Anime-Xmas-LoRA

❄️Collections
+ [ Xmas Art ] : strangerzonehf/christmas-pack-6758b199487adafaddb68f82
+ [ Stranger Zone Collection ] : prithivMLmods/stranger-zone-collections-org-6737118adcf2cb40d66d0c7e

🥶Page
+ [ Stranger Zone ] : https://huggingface.co/strangerzonehf

.
.
.
@prithivMLmods 🤗

Jordan Legg PRO

AI & ML interests

Recent Activity

Organizations

takarajordan's activity

Amazing work