ibm-granite/granite-8b-code-instruct-4k
Full fine-tune vs ibm-granite/granite-8b-code-base-4k. Fine-tune: 100% of the weights changed, across 36 of 36 layers.
Tensors changed: Embeddings 1/1, Norms 73/73, MLP 216/216, Attention 288/288
6 derivatives checked
- mradermacher/granite-8b-code-instruct-i1-GGUF: Full fine-tune
- mradermacher/granite-8b-code-instruct-4k-i1-GGUF: Full fine-tune
- mradermacher/granite-8b-code-instruct-GGUF: Partial fine-tune
- mradermacher/granite-8b-code-instruct-4k-GGUF: Partial fine-tune
- DevQuasar-8/ibm-granite.granite-8b-code-instruct-4k-GGUF: Partial fine-tune
- tensorblock/granite-8b-code-instruct-4k-GGUF: Full fine-tune
1 other repos hold byte-for-byte identical weight files.