ibm-granite/granite-3.2-2b-instruct
Full fine-tune vs ibm-granite/granite-3.1-2b-instruct. Fine-tune: 100% of the weights changed, across 40 of 40 layers.
Tensors changed: Embeddings 1/1, Norms 59/81, MLP 120/120, Attention 160/160
10 derivatives checked
- EasierAI/Granite-3.2-2B: Quantization
- bartowski/ibm-granite_granite-3.2-2b-instruct-GGUF: Quantization
- ibm-research/granite-3.2-2b-instruct-GGUF: Same weights, converted
- mradermacher/granite-3.2-2b-instruct-i1-GGUF: Quantization
- DevQuasar-9/ibm-granite.granite-3.2-2b-instruct-GGUF: Same weights, converted
- lmstudio-community/granite-3.2-2b-instruct-GGUF: Quantization
- unsloth/granite-3.2-2b-instruct-unsloth-bnb-4bit: Quantization
- unsloth/granite-3.2-2b-instruct: Identical copy
- tensorblock/granite-3.2-2b-instruct-GGUF: Quantization
- agentlans/Maitre-Granite-3.2-2b-instruct: LoRA-style
2 other repos hold byte-for-byte identical weight files.