ckkissane / rlhf-shakespeare
Shakespeare transformer fine-tuned to generate positive sentiment samples using RLHF
☆10Updated 2 years ago
Alternatives and similar repositories for rlhf-shakespeare:
Users that are interested in rlhf-shakespeare are comparing it to the libraries listed below
- Reference implementation for Reward-Augmented Decoding: Efficient Controlled Text Generation With a Unidirectional Reward Model☆42Updated last year
- Minimum Description Length probing for neural network representations☆18Updated last week
- Code for the examples presented in the talk "Training a Llama in your backyard: fine-tuning very large models on consumer hardware" given…☆14Updated last year
- The repository contains code for Adaptive Data Optimization☆21Updated last month
- ☆24Updated last year
- ReBase: Training Task Experts through Retrieval Based Distillation☆28Updated 6 months ago
- Script for processing OpenAI's PRM800K process supervision dataset into an Alpaca-style instruction-response format☆27Updated last year
- ☆27Updated 2 weeks ago
- This is a new metric that can be used to evaluate faithfulness of text generated by LLMs. The work behind this repository can be found he…☆31Updated last year
- Anchored Preference Optimization and Contrastive Revisions: Addressing Underspecification in Alignment☆53Updated 4 months ago
- Measuring and Controlling Persona Drift in Language Model Dialogs☆15Updated 10 months ago
- Efficient Scaling laws and collaborative pretraining.☆13Updated 2 months ago
- ☆65Updated 6 months ago
- Small and Efficient Mathematical Reasoning LLMs☆71Updated 11 months ago
- Embedding Recycling for Language models☆38Updated last year
- [ACL 2023] Gradient Ascent Post-training Enhances Language Model Generalization☆29Updated 4 months ago
- ☆25Updated last year
- Engineering the state of RNN language models (Mamba, RWKV, etc.)☆32Updated 7 months ago
- ☆46Updated 2 months ago
- Understanding the correlation between different LLM benchmarks☆29Updated last year
- QAmeleon introduces synthetic multilingual QA data using PaLM, a 540B large language model. This dataset was generated by prompt tuning P…☆34Updated last year
- Large scale 4D parallelism pre-training for 🤗 transformers in Mixture of Experts *(still work in progress)*☆81Updated last year
- Code repo for "Model-Generated Pretraining Signals Improves Zero-Shot Generalization of Text-to-Text Transformers" (ACL 2023)☆22Updated last year
- Embroid: Unsupervised Prediction Smoothing Can Improve Few-Shot Classification☆11Updated last year
- The code implementation of MAGDi: Structured Distillation of Multi-Agent Interaction Graphs Improves Reasoning in Smaller Language Models…☆31Updated 11 months ago
- Repository for Skill Set Optimization☆12Updated 5 months ago
- We develop world models that can be adapted with natural language. Intergrating these models into artificial agents allows humans to effe…☆20Updated 11 months ago