Alternatives and similar repositories for mlx-rlhf:

Users that are interested in mlx-rlhf are comparing it to the libraries listed below

• s-smits / grpo-optuna
  Optimizing Causal LMs through GRPO with weighted reward functions and automated hyperparameter tuning using Optuna
  ☆39Updated 2 months ago
• Xalp / ECHO
  Official homepage for "Self-Harmonized Chain of Thought" (NAACL 2025)
  ☆91Updated 2 months ago
• axolotl-ai-cloud / grpo_code
  A fast, local, and secure approach for training LLMs for coding tasks using GRPO with WebAssembly and interpreter feedback.
  ☆21Updated last week
• Jaykef / mlx-rag-gguf
  Minimal, clean code implementation of RAG with mlx using gguf model weights
  ☆49Updated 11 months ago
• matthewrenze / jhu-concise-cot
  The Benefits of a Concise Chain of Thought on Problem Solving in Large Language Models
  ☆21Updated 4 months ago
• stockeh / mlx-optimizers
  A collection of optimizers for MLX
  ☆34Updated 3 weeks ago
• teknium1 / transformers-gptq-quant
  ☆48Updated last year
• N8python / mlx-gpt
  A simple MLX implementation for pretraining LLMs on Apple Silicon.
  ☆28Updated 2 months ago
• xjdr-alt / llmri
  look how they massacred my boy
  ☆63Updated 5 months ago
• google-deepmind / latent-multi-hop-reasoning
  [ACL 2024] Do Large Language Models Latently Perform Multi-Hop Reasoning?
  ☆60Updated 3 weeks ago
• ivanleomk / modal-grpo
  ☆18Updated 3 weeks ago
• xjdr-alt / muzero_sketch
  ☆38Updated 8 months ago
• SebastianBodza / EnsembleForecasting
  Using multiple LLMs for ensemble Forecasting
  ☆16Updated last year
• chimezie / mlx-tuning-fork
  Very basic framework for composable parameterized large language model (Q)LoRA / (Q)Dora fine-tuning using mlx, mlx_lm, and OgbujiPT.
  ☆37Updated last month
• N8python / n8loom
  A tree-based prefix cache library that allows rapid creation of looms: hierarchal branching pathways of LLM generations.
  ☆68Updated 2 months ago
• EduardTalianu / EntropixLab
  entropix style sampling + GUI
  ☆25Updated 5 months ago
• OpenPipe / deductive-reasoning
  Train your own SOTA deductive reasoning model
  ☆83Updated last month
• minosvasilias / simple_grpo
  Simple GRPO scripts and configurations.
  ☆58Updated 2 months ago
• AtakanTekparmak / tiny_fnc_engine
  tiny_fnc_engine is a minimal python library that provides a flexible engine for calling functions extracted from a LLM.
  ☆38Updated 7 months ago
• joey00072 / Attention-as-graph
  alternative way to calculating self attention
  ☆18Updated 10 months ago
• JD-P / RetroInstruct
  Synthetic data derived by templating, few shot prompting, transformations on public domain corpora, and monte carlo tree search.
  ☆31Updated last month
• AtakanTekparmak / agento
  Very minimal (and stateless) agent framework
  ☆41Updated 3 months ago
• zhuzilin / faster-nougat
  Implementation of nougat that focuses on processing pdf locally.
  ☆81Updated 2 months ago
• mzbac / mlx-lora
  ☆38Updated last year
• catid / lllm
  Latent Large Language Models
  ☆17Updated 7 months ago
• enjalot / latent-data-modal
  Using modal.com to process FineWeb-edu data
  ☆20Updated last week
• official-elinas / zeus-llm-trainer
  Zeus LLM Trainer is a rewrite of Stanford Alpaca aiming to be the trainer for all Large Language Models
  ☆69Updated last year
• austinsilveria / tricksy
  Fast approximate inference on a single GPU with sparsity aware offloading
  ☆38Updated last year
• deployradiant / pychatml
  Chat Markup Language conversation library
  ☆55Updated last year
• Zyphra / zcookbook
  Training hybrid models for dummies.
  ☆20Updated 2 months ago