aayush garg
garg-aayush
AI & ML interests
None yet
Organizations
Training-LLMs
- Running on CPU UpgradeFeatured3.22k
The Smol Training Playbook
📚3.22kThe secrets to building world-class LLMs
- Running3.9k
The Ultra-Scale Playbook
🌌3.9kThe ultimate guide to training LLM on large GPU Clusters
- RunningFeatured1.38k
FineWeb: decanting the web for the finest text data at scale
🍷1.38kExplore and download the FineWeb web‑scale text dataset
- Running230
FineVision: Open Data is All You Need
📝230A new open-source dataset for training VLMs
RLHF Papers
-
Proximal Policy Optimization Algorithms
Paper • 1707.06347 • Published • 11 -
Direct Preference Optimization: Your Language Model is Secretly a Reward Model
Paper • 2305.18290 • Published • 66 -
DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
Paper • 2402.03300 • Published • 148 -
DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
Paper • 2501.12948 • Published • 454
Llama papers and reports
List of papers and reports related to llama models
LLM Tech Reports
RLHF Papers
-
Proximal Policy Optimization Algorithms
Paper • 1707.06347 • Published • 11 -
Direct Preference Optimization: Your Language Model is Secretly a Reward Model
Paper • 2305.18290 • Published • 66 -
DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
Paper • 2402.03300 • Published • 148 -
DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
Paper • 2501.12948 • Published • 454
Training-LLMs
- Running on CPU UpgradeFeatured3.22k
The Smol Training Playbook
📚3.22kThe secrets to building world-class LLMs
- Running3.9k
The Ultra-Scale Playbook
🌌3.9kThe ultimate guide to training LLM on large GPU Clusters
- RunningFeatured1.38k
FineWeb: decanting the web for the finest text data at scale
🍷1.38kExplore and download the FineWeb web‑scale text dataset
- Running230
FineVision: Open Data is All You Need
📝230A new open-source dataset for training VLMs
Llama papers and reports
List of papers and reports related to llama models