SicariusSicariiStuff/Impish_Longtail_12B
Full fine-tune vs SicariusSicariiStuff/Impish_Nemo_12B. Fine-tune: 100% of the weights changed, across 40 of 40 layers.
Tensors changed: Embeddings 1/1, Norms 81/81, MLP 120/120, Attention 160/160, lm_head 1/1
9 derivatives checked
- mradermacher/Impish_Longtail_12B-i1-GGUF: Quantization
- SicariusSicariiStuff/Impish_Longtail_12B_GGUF: Quantization
- SicariusSicariiStuff/Impish_Longtail_12B_GGUF_HA: Quantization
- mradermacher/Impish_Longtail_12B-GGUF: Quantization
- SicariusSicariiStuff/Impish_Longtail_12B_iMatrix: Quantization
- Retreatcost/Chrysologus-12B: Full fine-tune
- Retreatcost/Impish-LongPen-12B: Full fine-tune
- Sicarius-Prototyping/Impish_Merge_Nemo_Longtail: Full fine-tune
- Rheinwehr/Kardinal-Nemo-12B: Full fine-tune