BlinkDL / WorldModel
Let us make Psychohistory (as in Asimov) a reality, and accessible to everyone. Useful for LLM grounding and games / fiction / business / finance / governance, and can align agents with human too.
☆40Updated last year
Alternatives and similar repositories for WorldModel:
Users that are interested in WorldModel are comparing it to the libraries listed below
- ☆42Updated last year
- Here we collect trick questions and failed tasks for open source LLMs to improve them.☆32Updated last year
- Demonstration that finetuning RoPE model on larger sequences than the pre-trained model adapts the model context limit☆63Updated last year
- RWKV-v2-RNN trained on the Pile. See https://github.com/BlinkDL/RWKV-LM for details.☆67Updated 2 years ago
- Zeta implementation of a reusable and plug in and play feedforward from the paper "Exponentially Faster Language Modeling"☆15Updated 4 months ago
- RWKV model implementation☆37Updated last year
- BigKnow2022: Bringing Language Models Up to Speed☆14Updated last year
- Trying to deconstruct RWKV in understandable terms☆14Updated last year
- Script for processing OpenAI's PRM800K process supervision dataset into an Alpaca-style instruction-response format☆27Updated last year
- Tools for content datamining and NLP at scale☆42Updated 9 months ago
- Evaluating LLMs with Dynamic Data☆78Updated last month
- This project aims to make RWKV Accessible to everyone using a Hugging Face like interface, while keeping it close to the R and D RWKV bra…☆64Updated last year
- Experiments with BitNet inference on CPU☆53Updated 11 months ago
- SparseGPT + GPTQ Compression of LLMs like LLaMa, OPT, Pythia☆41Updated 2 years ago
- GoldFinch and other hybrid transformer components☆45Updated 8 months ago
- ☆16Updated last year
- Official repository for the paper "Approximating Two-Layer Feedforward Networks for Efficient Transformers"☆36Updated last year
- Exploring finetuning public checkpoints on filter 8K sequences on Pile☆115Updated 2 years ago
- RWKV-7: Surpassing GPT☆82Updated 4 months ago
- 32 times longer context window than vanilla Transformers and up to 4 times longer than memory efficient Transformers.☆46Updated last year
- [NeurIPS 2023] Sparse Modular Activation for Efficient Sequence Modeling☆36Updated last year
- ☆31Updated 9 months ago
- Structural Pruning for LLaMA☆54Updated last year
- Framework agnostic python runtime for RWKV models☆145Updated last year
- Inference script for Meta's LLaMA models using Hugging Face wrapper☆110Updated 2 years ago
- ☆82Updated 10 months ago
- ☆40Updated last year
- RWKV in nanoGPT style☆187Updated 9 months ago
- RWKV, in easy to read code☆71Updated 3 months ago