mradermacher/llama-2-7b-monika-v0.3b-GGUF
Same weights, converted vs 922-CA/llama-2-7b-monika-v0.3b. Same weights stored in another dtype (F16/F32 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/65, MLP 0/96, Attention 0/128, lm_head 0/1
Same weights, converted vs 922-CA/llama-2-7b-monika-v0.3b. Same weights stored in another dtype (F16/F32 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/65, MLP 0/96, Attention 0/128, lm_head 0/1