Join the conversation

Join the community of Machine Learners and AI enthusiasts.

Sign Up

All HF Hub posts

Join Posts waitlist
posted an update about 1 hour ago
view post
I've just stumbled upon some excellent work on (πŸ‡«πŸ‡· French) retrieval models by @antoinelouis . Kudos to him!

- French Embedding Models: antoinelouis/dense-single-vector-bi-encoders-651523c0c75a3d4c44fc864d
- French Reranker Models: antoinelouis/cross-encoder-rerankers-651523f16efa656d1788a239
- French Multi-vector Models: antoinelouis/dense-multi-vector-bi-encoders-6589a8ee6b17c06872e9f075
- Multilingual Models: antoinelouis/modular-retrievers-65d53d0db64b1d644aea620c

A lot of these models use the MS MARCO Hard Negatives dataset, which I'm currently reformatting to be more easily usable. Notably, they should work out of the box without any pre-processing for training embedding models in the upcoming Sentence Transformers v3.
posted an update about 11 hours ago
view post
@rubend18 Hello Ruben, I have been trying to manipulate my Andriod and other phones for some time. Friends always ask, its a hit or miss. May I have access to your repo on the jailbreaking please.
  • 2 replies
posted an update about 12 hours ago
view post
πŸš€πŸŽ­πŸŒŸ New Research Alert - SIGGRAPH 2024 (Avatars Collection)! πŸŒŸπŸŽ­πŸš€
πŸ“„ Title: 3D Gaussian Blendshapes for Head Avatar Animation πŸ”

πŸ“ Description: 3D Gaussian Blendshapes for Head Avatar Animation is a novel method for modeling and animating photorealistic head avatars from monocular video input.

πŸ‘₯ Authors: Shengjie Ma, Yanlin Weng, Tianjia Shao, and Kun Zhou

πŸ“… Conference: SIGGRAPH, 28 Jul – 1 Aug, 2024 | Denver CO, USA πŸ‡ΊπŸ‡Έ

πŸ“„ Paper: 3D Gaussian Blendshapes for Head Avatar Animation (2404.19398)

🌐 Github Page:

πŸ“š More Papers: more cutting-edge research presented at other conferences in the DmitryRyumin/NewEraAI-Papers curated by @DmitryRyumin

πŸš€ Added to the Avatars Collection: DmitryRyumin/avatars-65df37cdf81fec13d4dbac36

πŸ” Keywords: #3DAnimation #HeadAvatar #GaussianBlendshapes #FacialAnimation #RealTimeRendering #SIGGRAPH2024 #ComputerGraphics #DeepLearning #ComputerVision #Innovation
posted an update about 13 hours ago
view post
I need someone with a PRO subscription to help me with a task πŸ˜… Anybody that can help ?
PS : I believe this won't add any charges to the person's acc!
posted an update about 13 hours ago
view post
πŸ”₯ Did you know that you can try out Play.HT 2.0 and OpenVoice V2 on the TTS Arena for free?

Enter text and vote on which model is superior!
posted an update about 16 hours ago
view post
678 Now transfered to ChemLLM-20B-DPO, Have a try now!πŸ€—
posted an update about 17 hours ago
view post
mlx_micrograd - mlx port of Karpathy's micrograd- a tiny scalar-valued autograd engine with a small PyTorch-like neural network library on top.
pip install mlx_micrograd

Example usage
Example showing a number of possible supported operations:
from mlx_micrograd.engine import Value

a = Value(-4.0)
b = Value(2.0)
c = a + b
d = a * b + b**3
c += c + 1
c += 1 + c + (-a)
d += d * 2 + (b + a).relu()
d += 3 * d + (b - a).relu()
e = c - d
f = e**2
g = f / 2.0
g += 10.0 / f
print(f'{}') # prints array(24.7041, dtype=float32), the outcome of this forward pass
print(f'{a.grad}') # prints array(138.834, dtype=float32), i.e. the numerical value of dg/da
print(f'{b.grad}') # prints array(645.577, dtype=float32), i.e. the numerical value of dg/db

posted an update 1 day ago
view post
Create and Train Your Own Expert LLM: Generating Synthetic, Fact-Based Datasets with LMStudio/Ollama and then fine-tuning with MLX and Unsloth

Hey everyone!

I know there are tons of videos and tutorials out there already but I've noticed a lot of questions popping up in community posts about using synthetic datasets for creative projects and how to transform personal content into more factual material. In my own work doing enterprise-level SFT and crafting my open-source models, I've enhanced a Python framework originally shared by the creator of the Tess models. This improved stack utilizes local language models and also integrates the Wikipedia dataset to ensure that the content generated is as accurate and reliable as possible.

I've been thinking of putting together a comprehensive, step-by-step course/guide on creating your own Expert Language Model. From dataset preparation and training to deployment on Hugging Face and even using something like AnythingLLM for user interaction. I'll walk you through each phase, clarifying complex concepts and troubleshooting common pitfalls.

Let me know if this interests you!

Most of the datasets and models I've made have been using these scripts and my approach
posted an update 2 days ago
view post
Midjourney Ai
posted an update 2 days ago
view post
Enhancing Distributed Systems with Self-Healing Nodes and Adaptive Data Sharding

Paper: Self-healing Nodes with Adaptive Data-Sharding (2405.00004)

The paper introduces an innovative approach to improve distributed systems by integrating self-healing nodes with adaptive data sharding. This method leverages advanced concepts like self-replication, fractal regeneration, and predictive sharding to enhance scalability, performance, fault tolerance, and adaptability.

Key Concepts:
- Self-Replication: Nodes can create copies of themselves or their data to aid in recovery and load balancing.
- Fractal Regeneration: Nodes can reconfigure and restore their functionality after partial damage, inspired by natural fractals.
- Predictive Sharding: Nodes can anticipate future data trends and proactively adjust data distribution to optimize performance.

The approach consists of four main steps:
- Temporal data sharding based on data's temporal characteristics.
- Self-replicating nodes to enhance data availability and reliability.
- Fractal regeneration for robust recovery mechanisms.
- Predictive sharding using consistent hashing to anticipate and adapt to future data trends.

Results and Analysis:
Experimental evaluations show that this approach outperforms existing data sharding techniques in scalability, performance, fault tolerance, and adaptability. The use of synthetic data and workload generators created realistic scenarios for testing.

The methodology can be applied to various domains such as distributed database systems, blockchain networks, IoT, and cloud computing, offering improvements in data distribution efficiency and system resilience.