kyegomez/ExaPython
Unleash the full potential of exascale LLMs on consumer-class GPUs, proven by extensive benchmarks, with no long-term adjustments and minimal learning curve.
(27 stars) (4 forks) (0 个已索引 issue) (0 个开放 good first issue)
仓库
kyegomez 的仓库
This paper presents a comprehensive analysis of Kurt G¨odel’s ontological proof for the existence of God, with particular focus on contemporary expansions and refinements of the original framework
(6 stars) (0 forks) (0 个已索引 issue) (0 个开放 good first issue)
Fast and memory-efficient exact attention coupled with the LION Optimizer for ultra fast performance
(0 stars) (0 forks) (0 个已索引 issue) (0 个开放 good first issue)
kyegomez/FRViTPython
An attempt to create the most accurate, reliable, and general vision transformers for facial recognition at scale.
(7 stars) (0 forks) (0 个已索引 issue) (0 个开放 good first issue)
kyegomez/FabLangShell
FabLang is a domain-specific programming language crafted to streamline industrial design and make parts easier to manufacture.
(4 stars) (0 forks) (0 个已索引 issue) (0 个开放 good first issue)
kyegomez/FaceNetsPython
Pretrained Facial Recognition Models to democratize access
(1 star) (1 fork) (0 个已索引 issue) (0 个开放 good first issue)
kyegomez/FalconPython
A simple package for leveraging Falcon 180B and the HF ecosystem's tools, including training/inference scripts, safetensors, integrations with bitsandbytes, PEFT, GPTQ, assisted generation, RoPE scaling support, and rich generation parameters.
(12 stars) (2 forks) (0 个已索引 issue) (0 个开放 good first issue)
kyegomez/FastFFPython
Zeta implementation of a reusable and plug in and play feedforward from the paper "Exponentially Faster Language Modeling"
(16 stars) (0 forks) (0 个已索引 issue) (0 个开放 good first issue)
kyegomez/Finetuning-SuiteJupyter Notebook
Finetune any model on HF in less than 30 seconds
(58 stars) (6 forks) (0 个已索引 issue) (0 个开放 good first issue)
kyegomez/FlamingoZetaPython
Flamingo Implemnted in Zeta + Pytorch primitives for high performance multi-modal learning
(7 stars) (0 forks) (0 个已索引 issue) (0 个开放 good first issue)
Get down and dirty with FlashAttention2.0 in pytorch, plug in and play no complex CUDA kernels
(115 stars) (7 forks) (0 个已索引 issue) (0 个开放 good first issue)
Triton implementation of Flash Attention2.0
(54 stars) (6 forks) (0 个已索引 issue) (0 个开放 good first issue)
kyegomez/FlashLoraPython
FlashAttention2.0 with Lora
(9 stars) (0 forks) (0 个已索引 issue) (0 个开放 good first issue)
kyegomez/FlashMHAJupyter Notebook
An simple pytorch implementation of Flash MultiHead Attention
(22 stars) (4 forks) (0 个已索引 issue) (0 个开放 good first issue)
kyegomez/Fusion3DPython
An extremely experimental model that intakes images and generates 3D scenes of those images using Diffusion
(8 stars) (1 fork) (0 个已索引 issue) (0 个开放 good first issue)
kyegomez/FuyuPython
Implementation of Adepts Fuyu all-new Multi-Modality model in pytorch
(24 stars) (3 forks) (0 个已索引 issue) (0 个开放 good first issue)
Unofficial GATO: Ready to train
(0 stars) (0 forks) (0 个已索引 issue) (0 个开放 good first issue)
kyegomez/GATSPython
Implementation of GATS from the paper: "GATS: Gather-Attend-Scatter" in pytorch and zeta
(8 stars) (0 forks) (0 个已索引 issue) (0 个开放 good first issue)
kyegomez/GPT3Python
An implementation of the base GPT-3 Model architecture from the paper by OPENAI "Language Models are Few-Shot Learners"
(22 stars) (4 forks) (0 个已索引 issue) (0 个开放 good first issue)
kyegomez/GPT4Python
The open source implementation of the base model behind GPT-4 from OPENAI [Language + Multi-Modal]
(10 stars) (2 forks) (0 个已索引 issue) (0 个开放 good first issue)