kashif
Principal Research Scientist working on Deep Learning, Time Series Forecasting, Reinforcement Learning and HPC.
Berlin, Germany
Pinned Repositories
ceres-solver
A Nonlinear Least Squares Minimizer
cuda-workshop
Code examples for the CUDA workshop
firedup
Clone of OpenAI's Spinning Up in PyTorch
ICLR2022-OpenReviewData
Crawl & visualize ICLR papers and reviews.
mathematica_cuda
Mathematica plug-in for CUDA
node-cuda
NVIDIA CUDA™ bindings for Node.js
node-geos
GEOS (Geometry Engine) bindings for Node.js
pytorch-transformer-ts
Repository of Transformer based PyTorch Time Series Models
tf-keras-tutorial
tf.keras + tf.data with Eager Execution
kashif's Repositories
kashif/pytorch-transformer-ts
Repository of Transformer based PyTorch Time Series Models
kashif/diffusers
kashif/vq-tr
VQ-TR repository
kashif/gluon-ts
GluonTS - Probabilistic Time Series Modeling in Python
kashif/time_match
kashif/iTransformer
Official implementation for "iTransformer: Inverted Transformers Are Effective for Time Series Forecasting".
kashif/trl
Train transformer language models with reinforcement learning.
kashif/ForecastPFN
kashif/accelerate
🚀 A simple way to train and use PyTorch models with multi-GPU, TPU, mixed-precision
kashif/alignment-handbook
Robust recipes for to align language models with human and AI preferences
kashif/blog
Public repo for HF blog posts
kashif/datasets
🤗 The largest hub of ready-to-use datasets for ML models with fast, easy-to-use and efficient data manipulation tools
kashif/llmtime
kashif/vector-quantize-pytorch
Vector Quantization, in Pytorch
kashif/chronos-forecasting
Chronos: Pretrained (Language) Models for Probabilistic Time Series Forecasting
kashif/distrax
kashif/evaluate
A library for easily evaluating machine learning models and datasets.
kashif/HoMM
High order Moment Models
kashif/hopfield-layers
Hopfield Networks is All You Need
kashif/lit-gpt
Hackable implementation of state-of-the-art open-source LLMs based on nanoGPT. Supports flash attention, 4-bit and 8-bit quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training. Apache 2.0-licensed.
kashif/mamba
kashif/minRF
kashif/mlx-examples
Examples in the MLX framework
kashif/notebooks
Notebooks using the Hugging Face libraries 🤗
kashif/pytorch-lightning
Pretrain, finetune and deploy AI models on multiple GPUs, TPUs with zero code changes.
kashif/RWKV-LM
RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.
kashif/summarize_from_feedback_details
kashif/timesfm
TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.
kashif/transformers
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
kashif/xformers
Hackable and optimized Transformers building blocks, supporting a composable construction.