b-re-w/Midm-2.0-Mini-Thinking

Full fine-tune vs K-intelligence/Midm-2.0-Mini-Instruct. Fine-tune: 100% of the weights changed, across 48 of 48 layers.

Tensors changed: Embeddings 1/1, Norms 97/97, MLP 144/144, Attention 192/192

2 derivatives checked

• mradermacher/Midm-2.0-Mini-Thinking-i1-GGUF: Full fine-tune
• mradermacher/Midm-2.0-Mini-Thinking-GGUF: Full fine-tune

On the Hub · Downloads on Model Pulse