automerger/Experiment24Ognoexperiment27-7B
Full fine-tune vs automerger/OgnoExperiment27-7B. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, Norms 65/65, MLP 96/96, Attention 128/128, lm_head 1/1
3 derivatives checked
- MaziyarPanahi/Experiment24Ognoexperiment27-7B-GGUF: Quantization
- MaziyarPanahi/Experiment28T3q_Experiment24Ognoexperiment27: Full fine-tune
- MaziyarPanahi/Experiment26Neuralsirkrishna_Experiment24Ognoexperiment27: Full fine-tune