nimanzik (Nima Nooshiri)

liked 2 Spaces 3 months ago

Token-In, Token-Out Done Right

🧩

7

Explore an interactive simulation while reading the article

physics-intern: an Autonomous Agent for Physics Research

📝

57

Explore an autonomous AI workflow for physics research

liked 4 Spaces 5 months ago

Distilling 100B+ Models 40x Faster with TRL

📝

93

TRL distillation for 100B+ teachers, 40x faster

The Synthetic Data Playbook: Generating Trillions of the Finest Tokens

📝

275

Visualize synthetic‑data experiments as an interactive bookshelf

The Smol Training Playbook

📚

3.28k

The secrets to building world-class LLMs

Evaluation Guidebook

📝

354

Explore LLM benchmark scores over time

liked a Space 6 months ago

QED-Nano: Teaching a Tiny Model to Prove Hard Theorems

📝

84

Who needs 1T parameters? Olympiad proofs with a 4B model

liked a Space 12 months ago

The Ultra-Scale Playbook

🌌

4k

The ultimate guide to training LLM on large GPU Clusters

liked 3 Spaces over 1 year ago

Can You Run It? LLM version

🚀

1.05k

Check if your GPU can run a chosen LLM model

Accelerate Presentation

🔥

16

Launch and train PyTorch models on any hardware with one command

Accelerate Examples

🌖

22

Generate code samples for model training and configuration

Nima Nooshiri

AI & ML interests

Organizations

Token-In, Token-Out Done Right

physics-intern: an Autonomous Agent for Physics Research

Distilling 100B+ Models 40x Faster with TRL

The Synthetic Data Playbook: Generating Trillions of the Finest Tokens

The Smol Training Playbook

Evaluation Guidebook

QED-Nano: Teaching a Tiny Model to Prove Hard Theorems

The Ultra-Scale Playbook

Can You Run It? LLM version

Accelerate Presentation

Accelerate Examples

Nima Nooshiri

AI & ML interests

Organizations

nimanzik's activity

Token-In, Token-Out Done Right

physics-intern: an Autonomous Agent for Physics Research

Distilling 100B+ Models 40x Faster with TRL

The Synthetic Data Playbook: Generating Trillions of the Finest Tokens

The Smol Training Playbook

Evaluation Guidebook

QED-Nano: Teaching a Tiny Model to Prove Hard Theorems

The Ultra-Scale Playbook

Can You Run It? LLM version

Accelerate Presentation

Accelerate Examples