sumo43 / loopvlm
run paligemma in real time
☆131Updated 10 months ago
Alternatives and similar repositories for loopvlm:
Users that are interested in loopvlm are comparing it to the libraries listed below
- Cerule - A Tiny Mighty Vision Model☆67Updated 7 months ago
- Full finetuning of large language models without large memory requirements☆93Updated last year
- an implementation of Self-Extend, to expand the context window via grouped attention☆119Updated last year
- ☆112Updated 3 months ago
- smolLM with Entropix sampler on pytorch☆151Updated 5 months ago
- An easy-to-understand framework for LLM samplers that rewind and revise generated tokens☆138Updated last month
- Run GGML models with Kubernetes.☆174Updated last year
- GRDN.AI app for garden optimization☆70Updated last year
- MLX port for xjdr's entropix sampler (mimics jax implementation)☆63Updated 5 months ago
- an open source reproduction of NVIDIA's nGPT (Normalized Transformer with Representation Learning on the Hypersphere)☆93Updated last month
- look how they massacred my boy☆63Updated 5 months ago
- Fully fine-tune large models like Mistral, Llama-2-13B, or Qwen-14B completely for free☆231Updated 5 months ago
- Video+code lecture on building nanoGPT from scratch☆66Updated 9 months ago
- Fast parallel LLM inference for MLX☆178Updated 9 months ago
- PyTorch implementation of models from the Zamba2 series.☆179Updated 2 months ago
- Train your own SOTA deductive reasoning model☆83Updated last month
- Simple Transformer in Jax☆136Updated 9 months ago
- A reinforcement learning framework based on MLX.☆233Updated last month
- LLaVA server (llama.cpp).☆179Updated last year
- Start a server from the MLX library.☆182Updated 8 months ago
- ☆112Updated last year
- ☆48Updated last year
- Generate Synthetic Data Using OpenAI, MistralAI or AnthropicAI☆223Updated 11 months ago
- ☆151Updated 4 months ago
- An mlx project to train a base model on your whatsapp chats using (Q)Lora finetuning☆166Updated last year
- Mistral7B playing DOOM☆130Updated 8 months ago
- Maybe the new state of the art vision model? we'll see 🤷♂️☆161Updated last year
- OpenCoconut implements a latent reasoning paradigm where we generate thoughts before decoding.☆170Updated 2 months ago
- ☆92Updated last year
- inference code for mixtral-8x7b-32kseqlen☆99Updated last year