robinsmits/Schaapje-2B-Pretrained

Full fine-tune vs ibm-granite/granite-3.0-2b-instruct. Fine-tune: 100% of the weights changed, across 40 of 40 layers.

Tensors changed: Embeddings 1/1, Norms 69/81, MLP 120/120, Attention 160/160

3 derivatives checked

• mradermacher/Schaapje-2B-Pretrained-i1-GGUF: Quantization
• mradermacher/Schaapje-2B-Pretrained-GGUF: Same weights, converted
• robinsmits/Schaapje-2B-Chat-SFT-V1.0: Full fine-tune

On the Hub · Downloads on Model Pulse