ibm-granite/granite-3.0-1b-a400m-instruct
Full fine-tune vs ibm-granite/granite-3.0-1b-a400m-base. Fine-tune: 100% of the weights changed, across 24 of 24 layers.
Tensors changed: other 72/72, Norms 49/49, Attention 96/96
6 derivatives checked
- bartowski/granite-3.0-1b-a400m-instruct-GGUF: Same weights, converted
- mradermacher/granite-3.0-1b-a400m-instruct-i1-GGUF: Quantization
- mradermacher/granite-3.0-1b-a400m-instruct-GGUF: Same weights, converted
- lmstudio-community/granite-3.0-1b-a400m-instruct-GGUF: Quantization
- DevQuasar-3/ibm-granite.granite-3.0-1b-a400m-instruct-GGUF: Quantization
- tensorblock/granite-3.0-1b-a400m-instruct-GGUF: Quantization