artindnr/ChatBerry
Partial fine-tune vs artindnr/strawberry-1. Partial change: 14% of the weights changed (attention, mlp), in 24 of 24 layers.
Tensors changed: Norms 0/49, MLP 6/144, Embeddings 0/1, Attention 96/216, lm_head 0/1
4 derivatives checked
- artindnr/ChatBerry-i1-GGUF: Quantization
- mradermacher/ChatBerry-i1-GGUF: Quantization
- artindnr/ChatBerry-GGUF: Quantization
- mradermacher/ChatBerry-GGUF: Quantization