spow12/ChatWaifu_2.0_vision

Full fine-tune vs mistral-experimental/pixtral-12b. Fine-tune: 93% of the weights changed, across 40 of 40 layers.

Tensors changed: Embeddings 0/1, Norms 0/130, MLP 189/192, Attention 252/256, other 2/5, lm_head 1/1

2 derivatives checked

• mradermacher/ChatWaifu_2.0_vision-i1-GGUF: Quantization (fewer layers)
• mradermacher/ChatWaifu_2.0_vision-GGUF: Quantization (fewer layers)

On the Hub · Downloads on Model Pulse