dvruette / concept-guidanceLinks
Code accompanying the paper "A Language Model's Guide Through Latent Space". It contains functionality for training and using concept vectors that control the behavior of LLMs at inference time.
☆22Updated last year
Alternatives and similar repositories for concept-guidance
Users that are interested in concept-guidance are comparing it to the libraries listed below
Sorting:
- ☆59Updated last month
- ☆55Updated last year
- Multi-Domain Expert Learning☆67Updated last year
- A framework for pitting LLMs against each other in an evolving library of games ⚔☆34Updated 8 months ago
- Minimal (400 LOC) implementation Maximum (multi-node, FSDP) GPT training☆132Updated last year
- Large language models (LLMs) made easy, EasyLM is a one stop solution for pre-training, finetuning, evaluating and serving LLMs in JAX/Fl…☆78Updated last year
- Repository for "I am a Strange Dataset: Metalinguistic Tests for Language Models"☆45Updated 2 years ago
- Anchored Preference Optimization and Contrastive Revisions: Addressing Underspecification in Alignment☆61Updated last year
- Official repo for Learning to Reason for Long-Form Story Generation☆73Updated 8 months ago
- Repository for the code of the "PPL-MCTS: Constrained Textual Generation Through Discriminator-Guided Decoding" paper, NAACL'22☆66Updated 3 years ago
- Simple repository for training small reasoning models☆47Updated 11 months ago
- Synthetic data generation and benchmark implementation for "Episodic Memories Generation and Evaluation Benchmark for Large Language Mode…☆62Updated 3 months ago
- ☆124Updated 10 months ago
- ☆34Updated last year
- Code for the ICLR 2024 paper "How to catch an AI liar: Lie detection in black-box LLMs by asking unrelated questions"☆71Updated last year
- Simple GRPO scripts and configurations.☆59Updated 11 months ago
- ☆50Updated last year
- Demonstration that finetuning RoPE model on larger sequences than the pre-trained model adapts the model context limit☆63Updated 2 years ago
- ☆40Updated last year
- ☆53Updated last year
- Learning to Retrieve by Trying - Source code for Grounding by Trying: LLMs with Reinforcement Learning-Enhanced Retrieval☆51Updated last year
- ☆29Updated last year
- ☆39Updated last year
- Latent Diffusion Language Models☆70Updated 2 years ago
- Reference implementation for Reward-Augmented Decoding: Efficient Controlled Text Generation With a Unidirectional Reward Model☆45Updated 3 months ago
- Official repository for the paper "Approximating Two-Layer Feedforward Networks for Efficient Transformers"☆38Updated 7 months ago
- A repository for transformer critique learning and generation☆89Updated 2 years ago
- ☆40Updated 8 months ago
- ☆23Updated last year
- ☆55Updated last year