minchyeom/Letta-o1

Partial fine-tune vs ATH-MaaS/Marco-o1. Partial change: 18% of the weights changed (attention, lm_head), in 28 of 28 layers.

Tensors changed: Embeddings 0/1, Norms 0/57, MLP 0/84, Attention 112/196, lm_head 1/1

2 derivatives checked

• mradermacher/Letta-o1-i1-GGUF: Quantization
• mradermacher/Letta-o1-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse