nbeerbower/EVA-Gutenberg-Rombos-slerp-Qwen2.5-32B
Full fine-tune vs nbeerbower/EVA-Gutenberg3-Qwen2.5-32B. Fine-tune: 99% of the weights changed, across 64 of 64 layers.
Tensors changed: Embeddings 1/1, MLP 189/192, Attention 441/448, Norms 127/129, lm_head 1/1
4 derivatives checked
- mradermacher/EVA-Gutenberg-Rombos-slerp-Qwen2.5-32B-i1-GGUF: Quantization
- mradermacher/EVA-Gutenberg-Rombos-Qwen2.5-32B-i1-GGUF: Quantization
- mradermacher/EVA-Gutenberg-Rombos-slerp-Qwen2.5-32B-GGUF: Quantization
- mradermacher/EVA-Gutenberg-Rombos-Qwen2.5-32B-GGUF: Quantization