Comparison between base Gemma-3 and its GRPO-finetuned
This model is fine tuned on PHI-2 model with OASST1 dataset
HF stable-diffusion concepts library with custom loss func
This model is based on SmalLMv2 model from Llama
This is a first implementation on transformer
Tokenizer specific to odia language with 5000 tokens
This is an demo for model trained on Imagenet1k dataset.
