spow12/ChatWaifu_v1.4

Full fine-tune vs Epiculous/Violet_Twilight-v0.1. Fine-tune: 100% of the weights changed, across 40 of 40 layers.

Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 46/81, MLP 120/120, Attention 160/160

3 derivatives checked

• mradermacher/ChatWaifu_v1.4-i1-GGUF: Full fine-tune
• featherless-ai-quants/spow12-ChatWaifu_v1.4-GGUF: Quantization
• mradermacher/ChatWaifu_v1.4-GGUF: Full fine-tune

On the Hub · Downloads on Model Pulse