-
A simple model-free and value-function-free reinforcement learning model
-
-
minimind-v Public
Forked from jingyaogong/minimind-v🚀 「大模型」3小时从0训练27M参数的视觉多模态VLM！🌏 Train a 27M-parameter VLM from scratch in just 3 hours!
Python Apache License 2.0 UpdatedDec 13, 2024 -
minimind Public
Forked from jingyaogong/minimind🚀🚀 「大模型」3小时完全从0训练26M的小参数GPT！🌏 Train a 26M-parameter GPT from scratch in just 3 hours!
Python Apache License 2.0 UpdatedDec 13, 2024 -
Cullama Public
Customize Your Own Llama Attention! No peft, no lora, only customizing your own llama attention to whatever you want!
Jupyter Notebook MIT License UpdatedAug 24, 2024 -
Awesome-Multimodal-Large-Language-Models Public
Forked from BradyFU/Awesome-Multimodal-Large-Language-Models✨✨Latest Advances on Multimodal Large Language Models
UpdatedAug 21, 2024 -
unsloth Public
Forked from unslothai/unslothFinetune Llama 3.1, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory
Python Apache License 2.0 UpdatedAug 13, 2024 -
stablediffusion Public
Forked from nlile/stablediffusionHigh-Resolution Image Synthesis with Latent Diffusion Models
Python MIT License UpdatedAug 9, 2024 -
nanoGPT Public
Forked from karpathy/nanoGPTThe simplest, fastest repository for training/finetuning medium-sized GPTs.
Python MIT License UpdatedAug 8, 2024 -
minGPT Public
Forked from karpathy/minGPTA minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training
Python MIT License UpdatedAug 6, 2024 -
gpt-fast Public
Forked from meta-pytorch/gpt-fastSimple and efficient pytorch-native transformer text generation in <1000 LOC of python.
Python BSD 3-Clause "New" or "Revised" License UpdatedAug 1, 2024 -
Taiwan-LLM Public
Forked from MiuLab/Taiwan-LLMTraditional Mandarin LLMs for Taiwan
Python Apache License 2.0 UpdatedJul 11, 2024 -
llama3-from-scratch Public
Forked from naklecha/llama3-from-scratchllama3 implementation one matrix multiplication at a time
Jupyter Notebook MIT License UpdatedMay 23, 2024 -
Deep_Neural_Game_Theory Public
It is a deep neural network combined with game theory
{{ message }}