Alternatives and similar repositories for effort

Users that are interested in effort are comparing it to the libraries listed below

• valine / training-hot-swap
  Pytorch script hot swap: Change code without unloading your LLM from VRAM
  ☆126Updated last month
• willccbb / mlx_parallm
  Fast parallel LLM inference for MLX
  ☆189Updated 10 months ago
• valine / NeuralFlow
  Visualize the intermediate output of Mistral 7B
  ☆362Updated 4 months ago
• umuthopeyildirim / DOOM-Mistral
  Mistral7B playing DOOM
  ☆131Updated 10 months ago
• EGjoni / DRUGS
  Stop messing around with finicky sampling parameters and just use DRµGS!
  ☆349Updated last year
• mlecauchois / micrograd-cuda
  ☆243Updated last year
• kayvr / token-hawk
  WebGPU LLM inference tuned by hand
  ☆150Updated last year
• recmo / cria
  Tiny inference-only implementation of LLaMA
  ☆93Updated last year
• N8python / mlx-pretrain
  A simple MLX implementation for pretraining LLMs on Apple Silicon.
  ☆76Updated last month
• sdan / selfextend
  an implementation of Self-Extend, to expand the context window via grouped attention
  ☆119Updated last year
• danielgross / ggml-k8s
  Run GGML models with Kubernetes.
  ☆172Updated last year
• llmonpy / needle-in-a-needlestack
  ☆116Updated 4 months ago
• exo-explore / mlx-bitnet
  1.58 Bit LLM on Apple Silicon using MLX
  ☆212Updated last year
• okuvshynov / slowllama
  Finetune llama2-70b and codellama on MacBook Air without quantization
  ☆447Updated last year
• antirez / gguf-tools
  GGUF implementation in C as a library and a tools CLI program
  ☆270Updated 4 months ago
• rentruewang / bocoel
  Bayesian Optimization as a Coverage Tool for Evaluating LLMs. Accurate evaluation (benchmarking) that's 10 times faster with just a few l…
  ☆284Updated last week
• Zyphra / Zamba2
  PyTorch implementation of models from the Zamba2 series.
  ☆181Updated 4 months ago
• PaulPauls / llama3_interpretability_sae
  A complete end-to-end pipeline for LLM interpretability with sparse autoencoders (SAEs) using Llama 3.2, written in pure PyTorch and full…
  ☆615Updated 2 months ago
• babycommando / neuralgraffiti
  Live-bending a foundation model’s output at neural network level.
  ☆254Updated last month
• euclaise / SlimTrainer
  Full finetuning of large language models without large memory requirements
  ☆93Updated last year
• Foreseerr / TScale
  ☆192Updated 3 weeks ago
• sumo43 / loopvlm
  run paligemma in real time
  ☆131Updated last year
• SinatrasC / entropix-smollm
  smolLM with Entropix sampler on pytorch
  ☆150Updated 7 months ago
• smolorg / smoltropix
  MLX port for xjdr's entropix sampler (mimics jax implementation)
  ☆64Updated 6 months ago
• xjdr-alt / entropix-local
  smol models are fun too
  ☆92Updated 6 months ago
• astramind-ai / BitMat
  An efficent implementation of the method proposed in "The Era of 1-bit LLMs"
  ☆153Updated 7 months ago
• philipturner / metal-flash-attention
  FlashAttention (Metal Port)
  ☆487Updated 8 months ago
• joennlae / tensorli
  Absolute minimalistic implementation of a GPT-like transformer using only numpy (<650 lines).
  ☆251Updated last year
• adamkarvonen / chess_llm_interpretability
  Visualizing the internal board state of a GPT trained on chess PGN strings, and performing interventions on its internal board state and …
  ☆205Updated 6 months ago
• Cerebras / gigaGPT
  a small code base for training large models
  ☆299Updated last month