ibm-granite/granite-speech-4.1-2b-nar
Full fine-tune vs ibm-granite/granite-4.0-1b-base. Fine-tune: 100% of the weights changed, across 40 of 40 layers.
Tensors changed: Embeddings 1/1, Norms 81/81, Attention 160/160
4 derivatives checked
- handy-computer/granite-speech-4.1-2b-nar-gguf: Not comparable yet
- cstr/granite-speech-4.1-2b-nar-GGUF: Not comparable yet
- mlx-community/granite-speech-4.1-2b-nar-mlx: Different architecture
- epapanita/granite-speech-4.1-2b-nar-gguf: Not comparable yet