openfree/WizardMath-AgentEvol-7B
Full fine-tune vs AgentGym/AgentEvol-7B. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Norms 65/65, MLP 96/96, Attention 128/128
2 derivatives checked
- mradermacher/WizardMath-AgentEvol-7B-i1-GGUF: Quantization
- mradermacher/WizardMath-AgentEvol-7B-GGUF: Same weights, converted
3 other repos hold byte-for-byte identical weight files.