jasonvanf / llama-trl
LLaMA-TRL: Fine-tuning LLaMA with PPO and LoRA
☆185Updated last year
Related projects ⓘ
Alternatives and complementary repositories for llama-trl
- 🐋 An unofficial implementation of Self-Alignment with Instruction Backtranslation.☆133Updated 5 months ago
- Finetuning LLaMA with RLHF (Reinforcement Learning with Human Feedback) based on DeepSpeed Chat☆107Updated last year
- A large-scale, fine-grained, diverse preference dataset (and models).☆315Updated 10 months ago
- Deita: Data-Efficient Instruction Tuning for Alignment [ICLR2024]☆500Updated 6 months ago
- InsTag: A Tool for Data Analysis in LLM Supervised Fine-tuning☆218Updated last year
- All available datasets for Instruction Tuning of Large Language Models☆237Updated 11 months ago
- [NAACL'24] Self-data filtering of LLM instruction-tuning data using a novel perplexity-based difficulty score, without using any other mo…☆308Updated 2 months ago
- ☆259Updated last year
- Codes and Data for Scaling Relationship on Learning Mathematical Reasoning with Large Language Models☆221Updated 2 months ago
- A curated list of Human Preference Datasets for LLM fine-tuning, RLHF, and eval.☆318Updated last year
- Generative Judge for Evaluating Alignment☆218Updated 10 months ago
- [ICML 2024] LESS: Selecting Influential Data for Targeted Instruction Tuning☆376Updated last month
- ☆94Updated last year
- Unofficial implementation of AlpaGasus☆84Updated last year
- Official repository of NEFTune: Noisy Embeddings Improves Instruction Finetuning☆384Updated 6 months ago
- train llama on a single A100 80G node using 🤗 transformers and 🚀 Deepspeed Pipeline Parallelism☆208Updated last year
- [ACL'24] Superfiltering: Weak-to-Strong Data Filtering for Fast Instruction-Tuning☆126Updated 2 months ago
- Repository for Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions, ACL23☆173Updated 5 months ago
- ☆265Updated 11 months ago
- ☆254Updated last month
- [EMNLP 2024] LongAlign: A Recipe for Long Context Alignment of LLMs☆221Updated 7 months ago
- Data and Code for Program of Thoughts (TMLR 2023)☆243Updated 6 months ago
- Scripts of LLM pre-training and fine-tuning (w/wo LoRA, DeepSpeed)☆70Updated 9 months ago
- Counting-Stars (★)☆76Updated 2 months ago
- This is the repository that contains the source code for the Self-Evaluation Guided MCTS for online DPO.☆199Updated 3 months ago
- ☆129Updated 4 months ago
- Scripts for fine-tuning Llama2 via SFT and DPO.☆186Updated last year
- ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search (NeurIPS 2024)☆325Updated last month
- [SIGIR'24] The official implementation code of MOELoRA.☆127Updated 4 months ago
- RLHF implementation details of OAI's 2019 codebase☆154Updated 10 months ago