mradermacher/Llama3-1B-Base-GGUF
Same weights, converted vs andrijdavid/Llama3-1B-Base. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/7, MLP 0/9, Attention 0/12
Same weights, converted vs andrijdavid/Llama3-1B-Base. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/7, MLP 0/9, Attention 0/12