backyardai/Esper-70B-GGUF
Same weights, converted vs ValiantLabs/CodeLlama-70B-Esper. Same weights stored in another dtype (F32 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/161, MLP 0/240, Attention 0/320, lm_head 0/1
Same weights, converted vs ValiantLabs/CodeLlama-70B-Esper. Same weights stored in another dtype (F32 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/161, MLP 0/240, Attention 0/320, lm_head 0/1