bunnycore/Qwen-2.5-7b-TitanFusion-v3

Full fine-tune vs Orion-zhen/Qwen2.5-7B-Instruct-Uncensored. Fine-tune: 93% of the weights changed, across 28 of 28 layers.

Tensors changed: Embeddings 0/1, Norms 16/57, MLP 84/84, Attention 134/196, lm_head 1/1

2 derivatives checked

• mradermacher/Qwen-2.5-7b-TitanFusion-v3-i1-GGUF: Quantization
• mradermacher/Qwen-2.5-7b-TitanFusion-v3-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse