mradermacher/llama-3-8b-1m-PoSE-GGUF
Same weights, converted vs winglian/llama-3-8b-1m-PoSE. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/65, MLP 0/96, Attention 0/128, lm_head 0/1
Same weights, converted vs winglian/llama-3-8b-1m-PoSE. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/65, MLP 0/96, Attention 0/128, lm_head 0/1