mnoorfawi - Hackdot

Selective fine-tuning of Language Models with Spectrum

Posted by mnoorfawi on Tuesday September 03, 2024 @06:58PM
from the huggingface.co dept.

https://huggingface.co/blog/anakin87/spectrum

( Read More... | no comments | 2 points | on HN )

More Than Fine: Multi-LoRA Support Now Available in Nvidia RTX AI Toolkit

Posted by mnoorfawi on Wednesday August 28, 2024 @05:32PM
from the blogs.nvidia.com dept.

https://blogs.nvidia.com/blog/ai-decoded-multi-lora-rtx/

( Read More... | no comments | on HN )

TableBench: A Comprehensive and Complex Benchmark for Table Question Answering

Posted by mnoorfawi on Thursday August 22, 2024 @10:35PM
from the arxiv.org dept.

https://arxiv.org/abs/2408.09174

( Read More... | no comments | 2 points | on HN )

Show HN: Bayesian Neural Networks and Uncertainty for Inferring Unseen Classes

Posted by mnoorfawi on Monday August 19, 2024 @11:45AM
from the show-hn dept.

https://github.com/MNoorFawi/bayesian-neural-networks-for-novel-class

( Read More... | no comments | 2 points | on HN )

Entity Linking and Relationship Extraction with Relik in LlamaIndex

Posted by mnoorfawi on Saturday August 17, 2024 @09:36PM
from the neo4j.com dept.

https://neo4j.com/developer-blog/entity-linking-relationship-extraction-relik-llamaindex/

( Read More... | no comments | 2 points | on HN )

An Introduction to Time Series Forecasting with Generative AI

Posted by mnoorfawi on Saturday August 17, 2024 @09:35PM
from the databricks.com dept.

https://www.databricks.com/blog/introduction-time-series-forecasting-generative-ai

( Read More... | no comments | 2 points | on HN )

Show HN: Python Compression Suite for Pandas DataFrames, CSV and Excel Files

Posted by mnoorfawi on Saturday August 17, 2024 @06:35PM
from the show-hn dept.

https://github.com/MNoorFawi/lzhw

( Read More... | 3 comments | 3 points | on HN )

Layerwise Recurrent Router for Mixture-of-Experts

Posted by mnoorfawi on Thursday August 15, 2024 @06:02PM
from the arxiv.org dept.

https://arxiv.org/abs/2408.06793

( Read More... | no comments | on HN )

Show HN: Locality-Sensitive Hashing in Python for Faster Nearest Neighbor Search

Posted by mnoorfawi on Thursday August 15, 2024 @05:41PM
from the show-hn dept.

https://github.com/MNoorFawi/lshashing

( Read More... | no comments | 2 points | on HN )

Nvidia NVLink and Nvidia NVSwitch Supercharge Large Language Model Inference

Posted by mnoorfawi on Tuesday August 13, 2024 @07:47PM
from the developer.nvidia.com dept.

https://developer.nvidia.com/blog/nvidia-nvlink-and-nvidia-nvswitch-supercharge-large-language-model-inference/

( Read More... | no comments | 2 points | on HN )

Are emergent abilities in large language models just in-context learning?

Posted by mnoorfawi on Tuesday August 13, 2024 @07:16PM
from the techxplore.com dept.

https://techxplore.com/news/2024-08-emergent-abilities-large-language-context.html

( Read More... | 1 comment | on HN )

FalconMamba 7B: The first attention-free and general-purpose pure Mamba model

Posted by mnoorfawi on Tuesday August 13, 2024 @06:21PM
from the huggingface.co dept.

https://huggingface.co/blog/falconmamba

( Read More... | no comments | 6 points | on HN )

AI orchestration: benefits, best practices, and tools

Posted by mnoorfawi on Tuesday August 13, 2024 @06:07PM
from the blog.n8n.io dept.

https://blog.n8n.io/ai-orchestration/

( Read More... | no comments | on HN )

Long Context RAG Performance of LLMs

Posted by mnoorfawi on Tuesday August 13, 2024 @09:27AM
from the databricks.com dept.

https://www.databricks.com/blog/long-context-rag-performance-llms

( Read More... | no comments | 2 points | on HN )

Clustering the Manifold of the Embeddings Learned by Autoencoders

Posted by mnoorfawi on Sunday August 11, 2024 @06:06AM
from the minimatech.org dept.

https://minimatech.org/autoencoder-with-manifold-learning-for-clustering-in-python/

( Read More... | no comments | on HN )

Build a Knowledge Graph-Based Agent with Llama 3.1, Nvidia Nim, and LangChain

Posted by mnoorfawi on Saturday August 10, 2024 @06:00PM
from the neo4j.com dept.

https://neo4j.com/developer-blog/knowledge-graph-llama-nvidia-langchain/

( Read More... | no comments | 3 points | on HN )

Decoding How Nvidia's Latest RTX-Powered Tools Help Developers Accelerate AI

Posted by mnoorfawi on Monday August 05, 2024 @08:37PM
from the blogs.nvidia.com dept.

https://blogs.nvidia.com/blog/ai-decoded-siggraph-chat-rtx-update/

( Read More... | no comments | on HN )

Show HN: Recommendation engine with reinforcement learning and action embeddings

Posted by mnoorfawi on Monday August 05, 2024 @08:34PM
from the show-hn dept.

https://github.com/MNoorFawi/building-recommendation-engine-with-reinforcement-learning

( Read More... | no comments | on HN )

Mem0: The Memory Layer for Personalized AI

Posted by mnoorfawi on Thursday August 01, 2024 @07:36PM
from the github.com dept.

https://github.com/mem0ai/mem0

( Read More... | no comments | 2 points | on HN )

Show HN: Pytholog library – Logic programming and backtracking in Python

Posted by mnoorfawi on Saturday July 27, 2024 @11:59AM
from the show-hn dept.

https://github.com/MNoorFawi/pytholog

( Read More... | no comments | on HN )

LAVE: Zero-Shot VQA Evaluation on Docmatix with LLMs

Posted by mnoorfawi on Friday July 26, 2024 @08:06AM
from the huggingface.co dept.

https://huggingface.co/blog/zero-shot-vqa-docmatix

( Read More... | no comments | on HN )

Run Mistral 7B model using less than 4GB of memory on your Mac with CoreML

Posted by mnoorfawi on Tuesday July 23, 2024 @09:53AM
from the huggingface.co dept.

https://huggingface.co/blog/mistral-coreml

( Read More... | no comments | 11 points | on HN )

Quantum Reservoir Computing Scales Up to 108 Qubits for Quantum Machine Learning

Posted by mnoorfawi on Monday July 22, 2024 @05:36PM
from the thequantuminsider.com dept.

https://thequantuminsider.com/2024/07/22/researchers-report-quantum-reservoir-computing-scales-up-to-108-qubits-in-step-toward-real-world-quantum-machine-learning/

( Read More... | no comments | on HN )

Nvidia Offers Self-Paced Career Development in AI and Data Science

Posted by mnoorfawi on Monday July 22, 2024 @06:48AM
from the blogs.nvidia.com dept.

https://blogs.nvidia.com/blog/ai-data-science-career-development/

( Read More... | no comments | on HN )

Show HN: Fine-tune LLMs without catastrophic forgetting with CURLoRA approach

Posted by mnoorfawi on Sunday July 21, 2024 @10:13AM
from the show-hn dept.

https://github.com/MNoorFawi/curlora

( Read More... | no comments | on HN )

Scaling Diffusion Transformers to 16B Parameters

Posted by mnoorfawi on Friday July 19, 2024 @07:53PM
from the huggingface.co dept.

https://huggingface.co/papers/2407.11633

( Read More... | no comments | on HN )

Cake: a Rust framework for distributed inference of large models like LLama3

Posted by mnoorfawi on Friday July 19, 2024 @04:54PM
from the github.com dept.

https://github.com/evilsocket/cake

( Read More... | no comments | on HN )

Fine-tuning Llama-3 to get 90% of GPT-4's performance at a fraction of the cost

Posted by mnoorfawi on Friday July 19, 2024 @03:58PM
from the together.ai dept.

https://www.together.ai/blog/finetuning

( Read More... | no comments | 2 points | on HN )

Navigating the Challenges of LLM Fine Tuning and Catastrophic Forgetting

Posted by mnoorfawi on Friday July 19, 2024 @10:35AM
from the yurts.ai dept.

https://www.yurts.ai/blog/navigating-the-challenges-of-fine-tuning-and-catastrophic-forgetting