mergekit-community/Berry-Spark-7B
Full fine-tune vs ChaoticNeutrals/Very_Berry_Qwen2_7B. Fine-tune: 97% of the weights changed, across 24 of 24 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 47/49, MLP 69/72, Attention 161/168
2 derivatives checked
- mradermacher/Berry-Spark-7B-i1-GGUF: Quantization
- mradermacher/Berry-Spark-7B-GGUF: Same weights, converted