jasonvanf / llama-trl
LLaMA-TRL: Fine-tuning LLaMA with PPO and LoRA
β185Updated last year
Related projects β
Alternatives and complementary repositories for llama-trl
- π An unofficial implementation of Self-Alignment with Instruction Backtranslation.β133Updated 5 months ago
- Finetuning LLaMA with RLHF (Reinforcement Learning with Human Feedback) based on DeepSpeed Chatβ107Updated last year
- A large-scale, fine-grained, diverse preference dataset (and models).β315Updated 10 months ago
- Deita: Data-Efficient Instruction Tuning for Alignment [ICLR2024]β500Updated 6 months ago
- InsTag: A Tool for Data Analysis in LLM Supervised Fine-tuningβ218Updated last year
- All available datasets for Instruction Tuning of Large Language Modelsβ237Updated 11 months ago
- [NAACL'24] Self-data filtering of LLM instruction-tuning data using a novel perplexity-based difficulty score, without using any other moβ¦β308Updated 2 months ago
- β259Updated last year
- Codes and Data for Scaling Relationship on Learning Mathematical Reasoning with Large Language Modelsβ221Updated 2 months ago
- A curated list of Human Preference Datasets for LLM fine-tuning, RLHF, and eval.β318Updated last year
- Generative Judge for Evaluating Alignmentβ218Updated 10 months ago
- [ICML 2024] LESS: Selecting Influential Data for Targeted Instruction Tuningβ376Updated last month
- β94Updated last year
- Unofficial implementation of AlpaGasusβ84Updated last year
- Official repository of NEFTune: Noisy Embeddings Improves Instruction Finetuningβ384Updated 6 months ago
- train llama on a single A100 80G node using π€βtransformers and πβDeepspeed Pipeline Parallelismβ208Updated last year
- [ACL'24] Superfiltering: Weak-to-Strong Data Filtering for Fast Instruction-Tuningβ126Updated 2 months ago
- Repository for Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions, ACL23β173Updated 5 months ago
- β265Updated 11 months ago
- β254Updated last month
- [EMNLP 2024] LongAlign: A Recipe for Long Context Alignment of LLMsβ221Updated 7 months ago
- Data and Code for Program of Thoughts (TMLR 2023)β243Updated 6 months ago
- Scripts of LLM pre-training and fine-tuning (w/wo LoRA, DeepSpeed)β70Updated 9 months ago
- Counting-Stars (β )β76Updated 2 months ago
- This is the repository that contains the source code for the Self-Evaluation Guided MCTS for online DPO.β199Updated 3 months ago
- β129Updated 4 months ago
- Scripts for fine-tuning Llama2 via SFT and DPO.β186Updated last year
- ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search (NeurIPS 2024)β325Updated last month
- [SIGIR'24] The official implementation code of MOELoRA.β127Updated 4 months ago
- RLHF implementation details of OAI's 2019 codebaseβ154Updated 10 months ago