IAmTheCollector/MN-Slush-GGLD

Full fine-tune vs DavidAU/MN-GRAND-Gutenberg-Lyra4-Lyra-12B-DARKNESS. Fine-tune: 100% of the weights changed, across 40 of 40 layers.

Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 35/81, MLP 120/120, Attention 160/160

4 derivatives checked

• mradermacher/MN-Slush-GGLD-i1-GGUF: Quantization
• mradermacher/MN-Slush-GGLD-GGUF: Quantization
• IAmTheCollector/MN-Slush-GGLD-Wayfarer: Full fine-tune
• mergekit-community/Slush-Sunfall-Rocinante-GGLD-12B: Partial fine-tune

On the Hub · Downloads on Model Pulse