Alternatives and similar repositories for tricksy:

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

• SebastianBodza / EnsembleForecasting
  Using multiple LLMs for ensemble Forecasting
  ☆16Updated last year
• ElleLeonne / Lightning-ReLoRA
  A public implementation of the ReLoRA pretraining method, built on Lightning-AI's Pytorch Lightning suite.
  ☆33Updated last year
• arcee-ai / DAM
  ☆48Updated 5 months ago
• matthewrenze / jhu-concise-cot
  The Benefits of a Concise Chain of Thought on Problem Solving in Large Language Models
  ☆22Updated 5 months ago
• 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
• Birch-san / booru-embed
  [WIP] Transformer to embed Danbooru labelsets
  ☆13Updated last year
• EduardTalianu / EntropixLab
  entropix style sampling + GUI
  ☆26Updated 6 months ago
• minosvasilias / simple_grpo
  Simple GRPO scripts and configurations.
  ☆58Updated 3 months ago
• mzbac / mlx-moe
  Scripts to create your own moe models using mlx
  ☆89Updated last year
• LLM360 / crystalcoder-data-prep
  Data preparation code for CrystalCoder 7B LLM
  ☆44Updated 11 months ago
• cognitivecomputations / kraken
  ☆66Updated 11 months ago
• kyegomez / Finetuning-Suite
  Finetune any model on HF in less than 30 seconds
  ☆58Updated last month
• attashe / ModifiedBeamSampler
  Modified Beam Search with periodical restart
  ☆12Updated 7 months ago
• nyunAI / PruneGPT
  ☆53Updated 11 months ago
• zarakiquemparte / zaraki-tools
  ☆27Updated last year
• sdan / selfextend
  an implementation of Self-Extend, to expand the context window via grouped attention
  ☆119Updated last year
• serp-ai / Parameter-Efficient-MoE
  Parameter-Efficient Sparsity Crafting From Dense to Mixture-of-Experts for Instruction Tuning on General Tasks
  ☆31Updated 11 months ago
• tval2 / contextual-pruning
  Library to facilitate pruning of LLMs based on context
  ☆32Updated last year
• BlinkDL / modded-nanogpt-rwkv
  RWKV-7: Surpassing GPT
  ☆83Updated 5 months ago
• euclaise / supertrainer2000
  ☆49Updated last year
• Cerebras / DocChat
  GPT-4 Level Conversational QA Trained In a Few Hours
  ☆60Updated 8 months ago
• RWKV / ZeroCoT
  https://x.com/BlinkDL_AI/status/1884768989743882276
  ☆27Updated this week
• axolotl-ai-cloud / grpo_code
  A fast, local, and secure approach for training LLMs for coding tasks using GRPO with WebAssembly and interpreter feedback.
  ☆22Updated last month
• diicellman / dynamite-dogs
  BH hackathon
  ☆14Updated last year
• s-smits / grpo-optuna
  Optimizing Causal LMs through GRPO with weighted reward functions and automated hyperparameter tuning using Optuna
  ☆39Updated 3 months ago
• tanyuqian / cappy
  NeurIPS 2023 - Cappy: Outperforming and Boosting Large Multi-Task LMs with a Small Scorer
  ☆43Updated last year
• 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
• SkunkworksAI / CodeFusion
  ☆15Updated last year
• andrew-silva / mlx-rlhf
  An example implementation of RLHF (or, more accurately, RLAIF) built on MLX and HuggingFace.
  ☆25Updated 10 months ago
• bdambrosio / AllTheWorldAPlay
  All the world is a play, we are but actors in it.
  ☆49Updated this week