ColossalChat: An Open-source Solution for Cloning ChatGPT with A Complete RLHF Pipeline | https://
syncedreview.com/2023/03/29/col
ossalchat-an-open-source-solution-for-cloning-chatgpt-with-a-complete-rlhf-pipeline/
…
#AI #ML #ArtificialIntelligence #MachineLearning #DeepNeuralNetwork
MACHINE LEARNING
-
ColossalChat: Open-source ChatGPT Cloning with Complete RLHF
By
–
-
Open Source Solution Replicates ChatGPT Training Efficiently
By
–
Open Source Solution Replicates ChatGPT Training Process! Ready To Go With Only 1.6GB GPU Memory And Gives You 7.73 Times Faster Training! | https://
syncedreview.com/2023/02/22/ope
n-source-solution-replicates-chatgpt-training-process-ready-to-go-with-only-1-6gb-gpu-memory-and-gives-you-7-73-times-faster-training/
…
#AI #ML #ArtificialIntelligence #MachineLearning #DeepNeuralNetwork -
Colossal-AI achieves 46x hardware savings for AIGC
By
–
Hardware Savings Up to 46 Times for AIGC and Automatic Parallelism in New Colossal-AI Release | https://
syncedreview.com/2023/01/04/har
dware-savings-up-to-46-times-for-aigc-and-automatic-parallelism-in-new-colossal-ai-release/
… #AI #ML #ArtificialIntelligence #MachineLearning #DeepNeuralNetwork -
Anthropic Releases Claude 2 Second Generation AI Chatbot
By
–
Anthropic releases Claude 2, its second-gen AI chatbot | TechCrunch https://
tcrn.ch/3DmIPC3. #AI #MachineLearning #DeepLearning #LLMs #DataScience -
Neural Operators for Sampling Diffusion Models at ICML
By
–
Come to @Kay12400259 presenting his work on using neural operators for sampling diffusion models @icmlconf
-
Spherical Fourier Neural Operators Achieve SOTA Weather Forecasting
By
–
A blog on our @icmlconf paper on spherical Fourier neural operator with SOTA medium-range weather forecast and long-term stability without any further training. Neural operators do zero-shot super-resolution. Adding spherical geometry enables them to capture fine-scale physics.
-
Sparse-IFT: Larger Sparse Models with Higher Accuracy
By
–
Sparse-IFT – Creating larger sparse models with higher accuracy at the same compute – https://
hubs.li/Q01Z9vCZ0 -
SparseGPT: Sparsifying LLMs for efficient inference
By
–
SparseGPT – Sparsifying LLMs for efficient inference – https://
hubs.li/Q01Z9ysx0 -
VSL: Variable Sequence Lengths for Cost-Effective Long Context
By
–
VSL – Utilizing variable sequence lengths to achieve longer sequences at lower cost – https://
hubs.li/Q01Z9jxc0 -
Sparse models match dense accuracy with fewer flops
By
–
SPDF – Matching the downstream accuracy of a dense model with a sparse model using fewer flops – https://
hubs.li/Q01Z9v0G0