HelpingAI/Dhanishtha-Large-RAW

Full fine-tune vs deepseek-ai/DeepSeek-R1-Distill-Qwen-7B. Fine-tune: 100% of the weights changed, across 28 of 28 layers.

Tensors changed: Attention 194/196, MLP 84/84, Norms 37/57

1 derivatives checked

• mradermacher/Dhanishtha-Large-RAW-GGUF: Same weights, converted

1 other repos hold byte-for-byte identical weight files.

On the Hub · Downloads on Model Pulse