SakanaAI / text-to-loraLinks
Hypernetworks that adapt LLMs for specific benchmark tasks using only textual task description as the input
☆831Updated last month
Alternatives and similar repositories for text-to-lora
Users that are interested in text-to-lora are comparing it to the libraries listed below
Sorting:
- Code to train and evaluate Neural Attention Memory Models to obtain universally-applicable memory systems for transformers.☆318Updated 9 months ago
- A Tree Search Library with Flexible API for LLM Inference-Time Scaling☆423Updated this week
- Build your own visual reasoning model☆399Updated 3 weeks ago
- Official repository for "DynaSaur: Large Language Agents Beyond Predefined Actions"☆346Updated 7 months ago
- Training teachers with reinforcement learning able to make LLMs learn how to reason for test time scaling.☆316Updated last month
- 🤗 Benchmark Large Language Models Reliably On Your Data☆367Updated this week
- ☆155Updated 3 months ago
- Self-Adapting Language Models☆733Updated last month
- Atom of Thoughts for Markov LLM Test-Time Scaling☆580Updated last month
- Code release for "LLMs can see and hear without any training"☆447Updated 2 months ago
- Inference, Fine Tuning and many more recipes with Gemma family of models☆260Updated 2 weeks ago
- Official python implementation of the UTCP☆364Updated this week
- A lightweight, local-first, and free experiment tracking Python library built on top of 🤗 Datasets and Spaces.☆339Updated this week
- CodeScientist: An automated scientific discovery system for code-based experiments☆287Updated last month
- Autonomously train research-agent LLMs on custom data using reinforcement learning and self-verification.☆648Updated 4 months ago
- Simple & Scalable Pretraining for Neural Architecture Research☆277Updated last week
- A-MEM: Agentic Memory for LLM Agents☆490Updated 2 weeks ago
- ☆163Updated 2 months ago
- A Self-adaptation Framework🐙 that adapts LLMs for unseen tasks in real-time!☆1,131Updated 6 months ago
- ☆220Updated 4 months ago
- GRPO training code which scales to 32xH100s for long horizon terminal/coding tasks. Base agent is now the top Qwen3 agent on Stanford's T…☆190Updated this week
- ☆219Updated last month
- Live-bending a foundation model’s output at neural network level.☆265Updated 3 months ago
- Build datasets using natural language☆505Updated 2 months ago
- DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation☆673Updated 3 weeks ago
- AlphaGo Moment for Model Architecture Discovery.☆794Updated this week
- The State Of The Art, intelligence☆134Updated this week
- Pretraining and inference code for a large-scale depth-recurrent language model☆806Updated 2 weeks ago
- GRadient-INformed MoE☆264Updated 10 months ago
- Synthetic data curation for post-training and structured data extraction☆1,464Updated 3 weeks ago