ckkissane / rlhf-shakespeare
Shakespeare transformer fine-tuned to generate positive sentiment samples using RLHF
☆10Updated last year
Related projects: ⓘ
- Large scale 4D parallelism pre-training for 🤗 transformers in Mixture of Experts *(still work in progress)*☆77Updated 9 months ago
- Script for processing OpenAI's PRM800K process supervision dataset into an Alpaca-style instruction-response format☆23Updated last year
- ☆27Updated 5 months ago
- Large language models (LLMs) made easy, EasyLM is a one stop solution for pre-training, finetuning, evaluating and serving LLMs in JAX/Fl…☆52Updated last month
- PyTorch implementation for MRL☆17Updated 6 months ago
- ☆29Updated 2 weeks ago
- ☆24Updated last year
- Reference implementation for Reward-Augmented Decoding: Efficient Controlled Text Generation With a Unidirectional Reward Model☆40Updated 8 months ago
- Small and Efficient Mathematical Reasoning LLMs☆69Updated 7 months ago
- Q-Probe: A Lightweight Approach to Reward Maximization for Language Models☆37Updated 3 months ago
- Code for the examples presented in the talk "Training a Llama in your backyard: fine-tuning very large models on consumer hardware" given…☆14Updated 11 months ago
- Collection of autoregressive model implementation☆62Updated 2 weeks ago
- A repository for research on medium sized language models.☆71Updated 3 months ago
- Repository for "I am a Strange Dataset: Metalinguistic Tests for Language Models"☆34Updated 8 months ago
- Here we provide and collect many functions to generate math problem and step by step solutions for LLM training☆17Updated last year
- Repository for Skill Set Optimization☆12Updated last month
- Minimal implementation of the Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models paper (ArXiv 20232401.01335)☆25Updated 6 months ago
- ☆45Updated 7 months ago
- Minimum Description Length probing for neural network representations☆15Updated 11 months ago
- ☆22Updated last year
- Official implementation of Goldfish Loss: Mitigating Memorization in Generative LLMs☆68Updated 2 months ago
- Critique-out-Loud Reward Models☆17Updated 2 weeks ago
- ☆25Updated 9 months ago
- Anchored Preference Optimization and Contrastive Revisions: Addressing Underspecification in Alignment☆39Updated 3 weeks ago
- QAmeleon introduces synthetic multilingual QA data using PaLM, a 540B large language model. This dataset was generated by prompt tuning P…☆33Updated last year
- ☆44Updated 2 months ago
- ☆18Updated this week
- ☆37Updated last year
- "Improving Mathematical Reasoning with Process Supervision" by OPENAI☆55Updated last week
- ☆50Updated last month