prithivMLmods/Lota-Carinae-Open-GRPO

Full fine-tune vs Qwen/Qwen2.5-1.5B-Instruct. Fine-tune: 100% of the weights changed, across 28 of 28 layers.

Tensors changed: Embeddings 1/1, Norms 57/57, MLP 84/84, Attention 196/196

2 derivatives checked

• mradermacher/Lota-Carinae-Open-GRPO-i1-GGUF: Quantization
• mradermacher/Lota-Carinae-Open-GRPO-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse