mradermacher/frankencria-llama2-11b-v1.3-m.1-GGUF

Same weights, converted vs davzoku/frankencria-llama2-11b-v1.3-m.1. Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: MLP 0/144, Norms 0/97, Attention 0/192, lm_head 0/1, Embeddings 0/1

On the Hub · Downloads on Model Pulse