| Name | Version | Summary | date |
| triton-xpu |
3.0.0b2 |
A language and compiler for custom Deep Learning operations |
2024-05-01 03:50:11 |
| REaLTabFormer |
0.1.7 |
A novel method for generating tabular and relational data using language models. |
2024-04-28 18:00:11 |
| bitnet |
0.2.5 |
bitnet - Pytorch |
2024-04-28 04:23:26 |
| termax |
0.1.4 |
Boost your terminal's intelligence with LLM: intuitive command assistance, seamless customization, and predictive next steps at your fingertips. |
2024-04-28 02:51:50 |
| FluxAI |
0.0.1 |
Lifelong Machine Learning Framework |
2024-04-28 02:25:23 |
| fastai |
2.7.15 |
fastai simplifies training fast and accurate neural nets using modern best practices |
2024-04-27 22:14:32 |
| llmtuner |
0.7.0 |
Easy-to-use LLM fine-tuning framework |
2024-04-27 19:50:40 |
| mh-moe |
0.0.2 |
Paper - Pytorch |
2024-04-27 00:01:23 |
| mm1-torch |
0.0.6 |
MM1 - Pytorch |
2024-04-26 16:17:01 |
| s5-pytorch |
0.2.1 |
S5 - Simplified State Space Layers for Sequence Modeling - Pytorch |
2024-04-26 09:39:13 |
| step-kit |
0.2.2 |
STEP, an acronym for Spatial Transcriptomics Embedding Procedure, is a deep learning-based tool for the analysis of single-cell RNA (scRNA-seq) and spatially resolved transcriptomics (SRT) data. STEP introduces a unified approach to process and analyze multiple samples of scRNA-seq data as well as align several sections of SRT data, disregarding location relationships. Furthermore, STEP conducts integrative analysis across different modalities like scRNA-seq and SRT. |
2024-04-25 17:18:19 |
| miditok |
3.0.3 |
MIDI / symbolic music tokenizers for Deep Learning models. |
2024-04-25 12:51:01 |
| gentab |
0.1.2 |
A synthetic tabular data generation library. |
2024-04-25 12:00:58 |
| routeagent |
0.1.2 |
RouteAgent: A Python package for route planning and evaluation with LLMs. |
2024-04-25 05:59:14 |
| soft-moe-pytorch |
0.1.8 |
Soft MoE - Pytorch |
2024-04-24 15:24:31 |
| deformable-attention |
0.0.19 |
Deformable Attention - from the paper "Vision Transformer with Deformable Attention" |
2024-04-23 23:45:52 |
| dmlcloud |
0.3.3 |
Distributed torch training using horovod and slurm |
2024-04-23 12:37:55 |
| BS-RoFormer |
0.4.1 |
BS-RoFormer - Band-Split Rotary Transformer for SOTA Music Source Separation |
2024-04-21 16:44:28 |
| eins |
0.1.1 |
One tensor operation is all you need |
2024-04-20 19:35:11 |
| ring-attention-pytorch |
0.4.1 |
Ring Attention - Pytorch |
2024-04-20 15:25:57 |