FourOhFour/Fatgirl_v2_8B

Full fine-tune vs FourOhFour/Magic_v2_8B. Fine-tune: 100% of the weights changed, across 40 of 40 layers.

Tensors changed: Embeddings 1/1, Norms 36/81, MLP 120/120, Attention 160/160, lm_head 1/1

4 derivatives checked

• mradermacher/Fatgirl_v2_8B-i1-GGUF: Quantization
• mradermacher/Fatgirl_v2_8B-GGUF: Same weights, converted
• hardlyworking/Emerald-8B: Full fine-tune
• jeiku/magicfatgirlv2: Full fine-tune

On the Hub · Downloads on Model Pulse