mergekit-community/Cute_Experiment-8B

Partial fine-tune vs crestf411/L3.1-8B-Slush-v1.1. Partial change: 81% of the weights changed (attention, mlp, norms), in 30 of 32 layers.

Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 57/65, MLP 90/96, Attention 120/128

2 derivatives checked

• mradermacher/Cute_Experiment-8B-i1-GGUF: Quantization
• mradermacher/Cute_Experiment-8B-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse