chai-research / lmgym
Code base for internal reward models and PPO training
☆24Updated last year
Alternatives and similar repositories for lmgym:
Users that are interested in lmgym are comparing it to the libraries listed below
- Exploring finetuning public checkpoints on filter 8K sequences on Pile☆115Updated 2 years ago
- Demonstration that finetuning RoPE model on larger sequences than the pre-trained model adapts the model context limit☆63Updated last year
- Multi-Domain Expert Learning☆67Updated last year
- Official repository for the paper "Approximating Two-Layer Feedforward Networks for Efficient Transformers"☆37Updated last year
- Script for processing OpenAI's PRM800K process supervision dataset into an Alpaca-style instruction-response format☆27Updated last year
- ☆49Updated last year
- Zeus LLM Trainer is a rewrite of Stanford Alpaca aiming to be the trainer for all Large Language Models☆69Updated last year
- Code repository for the c-BTM paper☆106Updated last year
- Spherical Merge Pytorch/HF format Language Models with minimal feature loss.☆120Updated last year
- Experiments with generating opensource language model assistants☆97Updated last year
- Code for the paper "The Impact of Positional Encoding on Length Generalization in Transformers", NeurIPS 2023☆135Updated 11 months ago
- A library for squeakily cleaning and filtering language datasets.☆47Updated last year
- 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
- GoldFinch and other hybrid transformer components☆45Updated 9 months ago
- QLoRA: Efficient Finetuning of Quantized LLMs☆78Updated last year
- Small and Efficient Mathematical Reasoning LLMs☆71Updated last year
- QLoRA with Enhanced Multi GPU Support☆37Updated last year
- ☆60Updated last year
- ☆32Updated 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
- Reference implementation for Reward-Augmented Decoding: Efficient Controlled Text Generation With a Unidirectional Reward Model☆43Updated last year
- Lightweight demos for finetuning LLMs. Powered by 🤗 transformers and open-source datasets.☆73Updated 6 months ago
- ☆20Updated last year
- Official implementation for 'Extending LLMs’ Context Window with 100 Samples'☆76Updated last year
- Collection of autoregressive model implementation☆85Updated 2 months ago
- [AAAI 2024] Investigating the Effectiveness of Task-Agnostic Prefix Prompt for Instruction Following☆79Updated 7 months ago
- Large Scale Distributed Model Training strategy with Colossal AI and Lightning AI☆57Updated last year
- ☆97Updated last year
- Anh - LAION's multilingual assistant datasets and models☆27Updated 2 years ago
- ☆84Updated last year