ibm-granite/granite-3.0-3b-a800m-instruct
Full fine-tune vs ibm-granite/granite-3.0-3b-a800m-base. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: other 96/96, Norms 65/65, Attention 128/128
4 derivatives checked
- bartowski/granite-3.0-3b-a800m-instruct-GGUF: Same weights, converted
- mradermacher/granite-3.0-3b-a800m-instruct-GGUF: Same weights, converted
- lmstudio-community/granite-3.0-3b-a800m-instruct-GGUF: Quantization
- MCZK/granite-3.0-3b-a800m-instruct-GGUF: Same weights, converted
1 other repos hold byte-for-byte identical weight files.