facebookresearch / Shepherd
This is the repo for the paper Shepherd -- A Critic for Language Model Generation
☆218Updated last year
Alternatives and similar repositories for Shepherd:
Users that are interested in Shepherd are comparing it to the libraries listed below
- Simple next-token-prediction for RLHF☆224Updated last year
- ☆172Updated last year
- [EMNLP 2023] The CoT Collection: Improving Zero-shot and Few-shot Learning of Language Models via Chain-of-Thought Fine-Tuning☆237Updated last year
- Benchmarking LLMs with Challenging Tasks from Real Users☆221Updated 5 months ago
- Self-Alignment with Principle-Following Reward Models☆158Updated last year
- ToolQA, a new dataset to evaluate the capabilities of LLMs in answering challenging questions with external tools. It offers two levels …☆257Updated last year
- Learning to Compress Prompts with Gist Tokens - https://arxiv.org/abs/2304.08467☆283Updated 2 months ago
- ☆268Updated last year
- This project studies the performance and robustness of language models and task-adaptation methods.☆149Updated 10 months ago
- DSIR large-scale data selection framework for language model training☆245Updated last year
- Official code for "MAmmoTH2: Scaling Instructions from the Web" [NeurIPS 2024]☆137Updated 5 months ago
- A large-scale, fine-grained, diverse preference dataset (and models).☆335Updated last year
- ☆121Updated 10 months ago
- ☆308Updated 10 months ago
- ☆159Updated 2 years ago
- Open Instruction Generalist is an assistant trained on massive synthetic instructions to perform many millions of tasks☆208Updated last year
- LOFT: A 1 Million+ Token Long-Context Benchmark☆184Updated last week
- Scripts for generating synthetic finetuning data for reducing sycophancy.☆109Updated last year
- Reverse Instructions to generate instruction tuning data with corpus examples☆209Updated last year
- A set of utilities for running few-shot prompting experiments on large-language models☆118Updated last year
- ☆178Updated 2 years ago
- Code for the paper "Rethinking Benchmark and Contamination for Language Models with Rephrased Samples"☆300Updated last year
- Scaling Data-Constrained Language Models☆335Updated 6 months ago
- LongEmbed: Extending Embedding Models for Long Context Retrieval (EMNLP 2024)☆132Updated 5 months ago
- The dataset and code for paper: TheoremQA: A Theorem-driven Question Answering dataset☆157Updated 11 months ago
- ☆236Updated 2 years ago
- Code and data accompanying our paper on arXiv "Faithful Chain-of-Thought Reasoning".☆157Updated 11 months ago
- Code and model release for the paper "Task-aware Retrieval with Instructions" by Asai et al.☆162Updated last year
- Open Source WizardCoder Dataset☆157Updated last year
- Code repository for the c-BTM paper☆106Updated last year