John Graham Reynolds PRO
MarioBarbeque
AI & ML interests
Quantum Computing, Mathematics+Code Generation, Deep Reasoning, Deep RL UT Austin Grad Student
Recent Activity
upvoted
a
collection
1 day ago
Catastrophic Forgetting in Mathematical Reasoning
updated
a collection
1 day ago
Catastrophic Forgetting in Mathematical Reasoning
updated
a collection
1 day ago
Catastrophic Forgetting in Mathematical Reasoning
Organizations
spaces
7
Sleeping
1
MistralAI
🚀
A retrieval-augmented chat model built with Mistral🇫🇷🦜
Sleeping
1
CyberSolve LinAlg 1.2
🤖
A 🤗 Space showing off the CyberSolve LinAlg 1.2 model
Sleeping
1
VanderbiltGlossary
🌰
A 🤗 Space for the first VUMC chatbot
Sleeping
1
FixedRecall
📉
A custom recall metric to fix a bug in 🤗 Evaluate
Sleeping
1
FixedPrecision
🎯
A custom precision metric to fix a bug in 🤗 Evaluate
Sleeping
1
FixedF1
📈
A custom f1 metric to fix a bug in 🤗 Evaluate
models
20
MarioBarbeque/flan-t5-base-math-only-catastrophic
0.2B
•
Updated
•
14
•
1
MarioBarbeque/flan-t5-base-nli-only-catastrophic
0.2B
•
Updated
•
12
•
1
MarioBarbeque/flan-t5-base-mixed-1-1-catastrophic
0.2B
•
Updated
•
22
•
1
MarioBarbeque/flan-t5-base-mixed-3-1-catastrophic
0.2B
•
Updated
•
17
•
1
MarioBarbeque/flan-t5-base-mixed-7-1-catastrophic
0.2B
•
Updated
•
17
•
1
MarioBarbeque/flan-t5-base-mixed-15-1-catastrophic
0.2B
•
Updated
•
22
•
1
MarioBarbeque/CyberSolve-LinAlg-1.2
0.8B
•
Updated
•
16
•
1
MarioBarbeque/dqn-SpaceInvadersNoFrameskip-v4
Reinforcement Learning
•
Updated
•
17
•
1
MarioBarbeque/q-Taxi-v3-2.0
Reinforcement Learning
•
Updated
•
1
MarioBarbeque/q-Taxi-v3
Reinforcement Learning
•
Updated
•
1
datasets
10
MarioBarbeque/StringTheorySolutions
Updated
•
21
•
1
MarioBarbeque/CyberSolve-LinAlg-1.2-correctness-benchmark
Viewer
•
Updated
•
10k
•
16
•
1
MarioBarbeque/CyberSolve-LinAlg-1.1-correctness-benchmark
Viewer
•
Updated
•
10k
•
13
•
1
MarioBarbeque/CyberSolve-DeepMind-LinAlg-1D-downsample-benchmark-v2
Viewer
•
Updated
•
10k
•
10
•
1
MarioBarbeque/CyberSolve-DeepMind-LinAlg-1D-downsample-benchmark
Viewer
•
Updated
•
10k
•
11
•
1
MarioBarbeque/FLAN-T5-DeepMind-LinAlg-1D-benchmark
Viewer
•
Updated
•
10k
•
14
•
1
MarioBarbeque/DeepMind-LinAlg-1D-eval
Viewer
•
Updated
•
10k
•
33
•
1
MarioBarbeque/DeepMind-LinAlg-1D-train
Viewer
•
Updated
•
2M
•
41
•
1
MarioBarbeque/hf-github-issues
Viewer
•
Updated
•
4k
•
23
•
1
MarioBarbeque/UCI_drug_reviews
Viewer
•
Updated
•
204k
•
14
•
1