Article
Deriving the PPO Loss from First Principles
•
19
Akshay Nuthanapati
a0308
·
AI & ML interests
Neural Networks, Large Language Models
Recent Activity
upvoted
an
article
1 day ago
Deriving the PPO Loss from First Principles
new activity
15 days ago
huggingface/InferenceSupport:haykgrigorian/v2mini-eval1
upvoted
an
article
about 1 month ago
Exploring Quantization Backends in Diffusers
Organizations
None yet
upvoted
an
article
1 day ago
upvoted
3
articles
about 1 month ago
Article
Exploring Quantization Backends in Diffusers
- +1
•
45
Article
Diffusers welcomes FLUX-2
- +6
•
165
Article
Continuous batching from first principles
- +1
•
286
upvoted
an
article
about 2 months ago
Article
SmolLM - blazingly fast and remarkably powerful
- +1
•
436
upvoted
5
articles
2 months ago
Article
Fine-Tuning Your First Large Language Model (LLM) with PyTorch and Hugging Face
•
93
Article
KV Cache from scratch in nanoVLM
- +3
•
106
Article
Proximal Policy Optimization (PPO)
•
71
Article
KV Caching Explained: Optimizing Transformer Inference Efficiency
•
202
Article
Get your VLM running in 3 simple steps on Intel CPUs
- +3
•
22
upvoted
a
paper
2 months ago
upvoted
an
article
2 months ago
Article
Welcome Gemma 3: Google's all new multimodal, multilingual, long context open LLM
-
- +2
•
479
upvoted
an
article
3 months ago
Article
Vision Language Models (Better, faster, stronger)
-
- +3
•
573
upvoted
a
paper
3 months ago
upvoted
6
articles
3 months ago
Article
Introducing Würstchen: Fast Diffusion for Image Generation
- +3
•
20
Article
How 🤗 Accelerate runs very large models thanks to PyTorch
•
16
Article
From PyTorch DDP to Accelerate to Trainer, mastery of distributed training with ease
•
42
Article
Efficient LLM Pretraining: Packed Sequences and Masked Attention
•
63
Article
DeepSeek-R1 Dissection: Understanding PPO & GRPO Without Any Prior Reinforcement Learning Knowledge
•
263
Article
There is no such thing as a tokenizer-free lunch
•
93