unsloth/whisper-large-v3

Same weights, converted vs openai/whisper-large-v3. Same weights stored in another dtype (F32 → F16).

Tensors changed: Embeddings 0/3, Attention 0/672, Norms 0/324, MLP 0/256, other 0/4

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

On the Hub · Downloads on Model Pulse