automerger/Inex12Experiment26-7B
Full fine-tune vs yam-peleg/Experiment26-7B. Fine-tune: 94% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, Norms 65/65, MLP 90/96, Attention 120/128, lm_head 1/1
4 derivatives checked
- MaziyarPanahi/Inex12Experiment26-7B-GGUF: Quantization
- mradermacher/Inex12Experiment26-7B-GGUF: Same weights, converted
- MaziyarPanahi/MeliodasPercival_01_Inex12Experiment26: Full fine-tune
- MaziyarPanahi/M7Yamshadowexperiment28_Inex12Experiment26: Full fine-tune