arvindanand/Deepseek-Wizard-33B-slerp
Full fine-tune (fewer layers) vs WizardLMTeam/WizardCoder-33B-V1.1. arvindanand/Deepseek-Wizard-33B-slerp matches part of WizardLMTeam/WizardCoder-33B-V1.1 (291 of its 561 tensors; the rest of WizardLMTeam/WizardCoder-33B-V1.1 has no counterpart). On the shared part: Fine-tune: 97% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, Norms 65/65, MLP 93/96, Attention 124/128, lm_head 1/1
1 derivatives checked
- mradermacher/Deepseek-Wizard-33B-slerp-GGUF: Quantization