Pinned Loading

1. deepseek deepseek Public

   deepseek architecture model

   Python

2. The-School-of-AI/LLM The-School-of-AI/LLM Public

   LightningLM 0.1V — Reference training pipeline for the LightningLM family. 2B dense seed → 5B MoE → 9B MoE → 120B sparse MoE through TurboQuant-PreTraining on a single eight-GPU node. Companion cod…

   Python 70 10

3. nanoGPT nanoGPT Public

   A GPT-2 architecture model trained on a very small dataset. ( please refer to README.md )

   Python

4. telugu_tokenizer telugu_tokenizer Public

   Tokenizer for telugu language ( less vocab )

   Python

5. resnet-cifar100 resnet-cifar100 Public

   ResNet with CIFAR100 from scratch ( using 1 cycle policy and Gradcam)

   Python

6. SmolLM2 SmolLM2 Public

   Reverse engineering of SmolLM2 from huggingface model

   Python