MysticFoxMagic/HeatherSpell-7b

Full fine-tune vs Kukedlc/NeuralExperiment-7b-MagicCoder-v7.5. Fine-tune: 97% of the weights changed, across 32 of 32 layers.

Tensors changed: Embeddings 1/1, Norms 65/65, MLP 93/96, Attention 124/128, lm_head 1/1

3 derivatives checked

• mradermacher/HeatherSpell-7b-GGUF: Quantization
• MysticFoxMagic/PandafishHeatherReReloaded: Full fine-tune
• MysticFoxMagic/PandafishHeatherReloaded: Full fine-tune

On the Hub · Downloads on Model Pulse