firstuserhere
Taking apart neural networks and putting them back together for a living. Personal website: https://kunvarthaman.com
firstuserhere's Stars
JoshuaDavid/utils_for_vastai
Personal utils for working with vast.ai. Probably not a good idea to use if you're not me.
irgolic/AutoPR
Run AI-powered workflows over your codebase
dion-/autoheal
AutoGPT Agent which automatically fixes your tests. GPT-powered TDD.
JoshuaDavid/sparse_coding
Using sparse coding to find distributed representations used by neural networks.
remyxai/FFMPerative
Chat to Compose Video
TransformerLensOrg/TransformerLens
A library for mechanistic interpretability of GPT-style language models
firstuserhere/hackathon-attention-superposition
firstuserhere/interp-hackathon-layernorm
Investigating the 4.39 problem from Concrete Open Problems
JiahuiYu/generative_inpainting
DeepFill v1/v2 with Contextual Attention and Gated Convolution, CVPR 2018, and ICCV 2019 Oral
mwatkins1970/SpellGPT
An experimental tool to explore GPT-3's "miraculous" ability not only to spell its own token strings (it being a "character blind" model) but also to use spelling as a means to produce novel outputs triggered by various "glitch tokens" (" SolidGoldMagikarp", et al.)
R0bk/Transpector
Visual Transformer Mechanistic Analysis Tool
noanabeshima/solu_moe_layer
ArthurConmy/Automatic-Circuit-Discovery
stanford-crfm/mistral
Mistral: A strong, northwesterly wind: Framework for transparent and accessible large-scale language model training, built with Hugging Face 🤗 Transformers.
UlisseMini/tinystories
Reproduction of TinyStories: How Small Can Language Models Be and Still Speak Coherent English?
mercari/ml-system-design-pattern
System design patterns for machine learning
1rgs/jsonformer
A Bulletproof Way to Generate Structured JSON from Language Models
openai/automated-interpretability
RobertHuben/ffn_via_attention
Implements the components of a transformer (including feedforward networks) entirely via attention heads
BorisTheBrave/nice-hooks
Convenience functions for working with pytorch hooks.
adzcai/llama-ccs
Running Contrast-Consistent Search (https://arxiv.org/abs/2212.03827) on LLaMA
thestephencasper/mechanistic_interpretability_challenge
amrzv/awesome-colab-notebooks
Collection of google colaboratory notebooks for fast and easy experiments
TransformerLensOrg/CircuitsVis
Mechanistic Interpretability Visualizations using React
hunar4321/reweight-gpt
Reweight GPT - a simple neural network using transformer architecture for next character prediction
firstuserhere/awesome-mech-interp
An awesome curated list of resources dedicated to Mechanistic interpretability
victorlf4/orthello-simple-trafo-mech-int
mwhea/Manifold_Trading_Bots
minosvasilias/gpt-manifold
An assistant for betting on prediction markets on manifold.markets, utilizing OpenAI's GPT APIs.
vluzko/manifoldpy
Python tools for working with Manifold Markets