zetasepic/Qwen2.5-32B-Instruct-abliterated-pass2

Partial fine-tune vs Qwen/Qwen2.5-32B-Instruct. Partial change: 70% of the weights changed (attention, embeddings, mlp), in 64 of 64 layers.

Tensors changed: Embeddings 1/1, Norms 0/129, MLP 128/192, Attention 256/448, lm_head 0/1

2 derivatives checked

• mradermacher/Qwen2.5-32B-Instruct-abliterated-pass2-i1-GGUF: Quantization
• mradermacher/Qwen2.5-32B-Instruct-abliterated-pass2-GGUF: Quantization

On the Hub · Downloads on Model Pulse