Repositories Users Organizations
Filter
Sort
wassname/ optuna-dashboard
TypeScript 0 0 0
Real-time Web Dashboard for Optuna.
Updated 2024-10-06 14:15:43 +08:00
wassname/ GENIES
Python 0 0 0
Generalization Analogies: A Testbed for Generalizing AI Oversight to Hard-To-Measure Domains
Updated 2024-08-25 15:06:10 +08:00
wassname/ baukit
Python 0 0 0
Updated 2024-08-07 21:50:03 +08:00
wassname/ viz_torch_optim
Jupyter Notebook 0 0 0
Videos of deep learning optimizers moving on 3D problem-landscapes
Updated 2024-07-25 18:12:05 +08:00
wassname/ lie_elicitation_prompts
Jupyter Notebook 0 0 0
Research dataset. We use prompts to get LLM's to lie. Using sys prompts and multi shot examples
Updated 2024-07-02 18:25:13 +08:00
wassname/ rag_search_cite
JavaScript 0 0 0
Hackable frontend for LLM assisted searching with citations
Updated 2024-06-29 20:18:49 +08:00
wassname/ LoRA_are_lie_detectors
Jupyter Notebook 0 0 0
Experiment to see if low rank adapters can work as interventions for lie detection on LLM's
Updated 2024-06-09 15:10:06 +08:00
wassname/ dreamerv3-torch
Python 0 0 0
Implementation of Dreamer v3 in pytorch.
Updated 2024-06-08 11:04:39 +08:00
wassname/ twm
Python 0 0 0
Transformer-based World Models
Updated 2024-06-03 20:17:02 +08:00
wassname/ jaxtyping
Python 0 0 0
Type annotations and runtime checking for shape and dtype of JAX/NumPy/PyTorch/etc. arrays. https://docs.kidger.site/jaxtyping/
Updated 2024-05-19 09:16:10 +08:00
wassname/ iris_bigvae
Jupyter Notebook 0 0 0
experiment: IRIS but with pretrained LLM
Updated 2024-05-11 10:28:00 +08:00
wassname/ discovering_latent_knowledge
Jupyter Notebook 0 0 0
Updated 2024-03-01 09:14:21 +08:00
wassname/ DebateTree
Python 0 0 0
A langchain app to visualise a debate using Tree-of-Thought reasoning
Updated 2024-02-25 09:22:14 +08:00
wassname/ stampy-chat
Python 0 0 0
Conversational chatbot to answer questions about AI Safety & Alignment based on information retrieved from the Alignment Research Dataset
Updated 2024-02-24 08:39:58 +08:00
wassname/ TTS
Python 0 0 0
🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production
Updated 2023-10-07 13:51:47 +08:00
wassname/ cr-dv3
Python 0 0 0
DreamerV3 implementation of Curious Replay, a method for prioritizing experience replay that is tailored to model-based reinforcement learning agents.
Updated 2023-07-05 23:06:45 +08:00
wassname/ seq2seq-time
Jupyter Notebook 0 0 0
Bechmarking seq2seq models on a range of multivariate regression datasets
Updated 2023-05-08 20:51:12 +08:00
wassname/ Ranger21
Python 0 0 0
Ranger deep learning optimizer rewrite to use newest components
Updated 2023-05-08 13:35:24 +08:00
wassname/ awesome-rlhf
0 0 0
Lists of datasets, training, and evals for RLHF and similar
Updated 2023-04-29 18:46:58 +08:00
wassname/ alpaca_convert
Python 0 0 0
Updated 2023-04-22 20:03:16 +08:00