Codingstark/gemma3-270m-leetcode

Same weights, converted vs unsloth/gemma-3-270m-it. Same weights stored in another dtype (BF16 → BF16/F16).

Tensors changed: Embeddings 0/1, Norms 0/109, MLP 0/54, Attention 0/72

1 other repos hold byte-for-byte identical weight files.

On the Hub · Downloads on Model Pulse