Sleeping
GRPO Training
📈
Comparison between base Gemma-3 and its GRPO-finetuned
Satya Nayak
satyanayak
·
AI & ML interests
Data Engineering, Generative AI
Recent Activity
updated
a Space
18 days ago
satyanayak/GRPO-Training
liked
a model
18 days ago
meta-llama/Llama-4-Scout-17B-16E-Instruct
updated
a model
19 days ago
satyanayak/gemma-3-GRPO
Organizations
None yet
spaces
8
Sleeping
First Agent Template
⚡
Find the current time in any timezone
Running
PHI2 SFT OASST1
📈
This model is fine tuned on PHI-2 model with OASST1 dataset
Sleeping
Stable Diffusion
📈
HF stable-diffusion concepts library with custom loss func
Sleeping
SmalLMv2 Text Generator
💻
This model is based on SmalLMv2 model from Llama
Sleeping
Transformer Basic
🏆
This is a first implementation on transformer
models
7
datasets
None public yet