Sleeping
Phi 2 Fine Tuned With GRPO
📈
Using DeepSeek's GRPO to fine tune Microsoft Phi-2!
Aditya Tiwari
atiwari751
AI & ML interests
None yet
Organizations
spaces 6
Sleeping
Fine Tuned Phi 2
👁
Microsoft Phi-2 model fine tuned on Open Assistant dataset.
Build error
Smollm2 135M Replica
👀
A replica of smollm2-135M trained on smollm corpus.
Sleeping
Agents
GPT2 Replica
👀
A decoder trained starting with GPT2 weights.
Build error
Hindi BPE Tokenizer
🔤
Build error
Agents
ResNet50 Image Classifier App
👀
A basic image classifier app built on ResNet 50 model.
datasets 0
None public yet