FareedKhan-dev / train-llama4Links
Building LLaMA 4 MoE from Scratch
☆67Updated 6 months ago
Alternatives and similar repositories for train-llama4
Users that are interested in train-llama4 are comparing it to the libraries listed below
Sorting:
- A Straightforward, Step-by-Step Implementation of a Video Diffusion Model☆64Updated 2 months ago
- Implementation of a GPT-4o like Multimodal from Scratch using Python☆73Updated 6 months ago
- LLaMA 3 is one of the most promising open-source model after Mistral, we will recreate it's architecture in a simpler manner.☆188Updated last year
- Building a 2.3M-parameter LLM from scratch with LLaMA 1 architecture.☆189Updated last year
- From scratch implementation of a vision language model in pure PyTorch☆246Updated last year
- Composition of Multimodal Language Models From Scratch☆15Updated last year
- minimal GRPO implementation from scratch☆98Updated 7 months ago
- ☆45Updated 5 months ago
- First-principle implementations of groundbreaking AI algorithms using a wide range of deep learning frameworks, accompanied by supporting…☆178Updated 3 months ago
- Fine tune Gemma 3 on an object detection task☆87Updated 3 months ago
- Maximizing the Performance of a Simple RAG using RL☆82Updated 7 months ago
- A minimal implementation of LLaVA-style VLM with interleaved image & text & video processing ability.☆96Updated 10 months ago
- ☆96Updated 7 months ago
- Easy to use, High Performant Knowledge Distillation for LLMs☆95Updated 5 months ago
- (ICCV 2025) OCR Hinders RAG: Evaluating the Cascading Impact of OCR on Retrieval-Augmented Generation☆92Updated 3 months ago
- An overview of GRPO & DeepSeek-R1 Training with Open Source GRPO Model Fine Tuning☆37Updated 5 months ago
- ☆102Updated last year
- nanoGRPO is a lightweight implementation of Group Relative Policy Optimization (GRPO)☆124Updated 5 months ago
- Parameter-efficient finetuning script for Phi-3-vision, the strong multimodal language model by Microsoft.☆58Updated last year
- Utils for Unsloth https://github.com/unslothai/unsloth☆162Updated this week
- Distributed training (multi-node) of a Transformer model☆85Updated last year
- This project is a collection of fine-tuning scripts to help researchers fine-tune Qwen 2 VL on HuggingFace datasets.☆74Updated 3 months ago
- RL significantly the reasoning capability of Qwen2.5-1.5B-Instruct☆30Updated 8 months ago
- Model compression toolkit engineered for enhanced usability, comprehensiveness, and efficiency.☆185Updated this week
- Tina: Tiny Reasoning Models via LoRA☆302Updated last month
- Learn the building blocks of how to build gpt-oss from scratch☆91Updated last month
- 🎈 A series of lightweight GPT models featuring TinyGPT Base (~51M params) and TinyGPT-MoE (~85M params). Fast, creative text generation …☆13Updated last month
- A new novel multi-modality (Vision) RAG architecture☆30Updated last year
- A straightforward method for training your LLM, from downloading data to generating text.☆455Updated 2 months ago
- Notes and commented code for RLHF (PPO)☆113Updated last year