ibm-granite/granite-3b-code-instruct-2k
Full fine-tune vs ibm-granite/granite-3b-code-base-2k. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, Norms 65/65, MLP 192/192, Attention 256/256
6 derivatives checked
- mradermacher/granite-3b-code-instruct-i1-GGUF: Full fine-tune
- mradermacher/granite-3b-code-instruct-2k-i1-GGUF: Full fine-tune
- mradermacher/granite-3b-code-instruct-2k-GGUF: Full fine-tune
- mradermacher/granite-3b-code-instruct-GGUF: Partial fine-tune
- DevQuasar-7/ibm-granite.granite-3b-code-instruct-2k-GGUF: Partial fine-tune
- tensorblock/granite-3b-code-instruct-2k-GGUF: Full fine-tune