tartuNLP/Apertus-EstLLM-8B-Instruct-1125

Full fine-tune vs tartuNLP/Apertus-EstLLM-8B-1125. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

Tensors changed: Embeddings 1/1, Norms 102/129, MLP 66/192, Attention 128/128, lm_head 1/1

2 derivatives checked

• mradermacher/Apertus-EstLLM-8B-Instruct-1125-i1-GGUF: Quantization
• mradermacher/Apertus-EstLLM-8B-Instruct-1125-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse