arcee-ai/arcee-blitz-caller-beta

Full fine-tune vs mistralai/Mistral-Small-24B-Base-2501. Fine-tune: 100% of the weights changed, across 40 of 40 layers.

Tensors changed: Norms 19/81, MLP 120/120, Attention 160/160

2 derivatives checked

• DevQuasar-9/arcee-ai.arcee-blitz-caller-beta-GGUF: Same weights, converted
• mradermacher/arcee-blitz-caller-beta-GGUF: Quantization

On the Hub · Downloads on Model Pulse