taharmasmaliyev07/Qwen2.5-3B-Instruct-Perplexity-E3-BF16

Full fine-tune vs unsloth/Qwen2.5-3B-Instruct. Fine-tune: 100% of the weights changed, across 36 of 36 layers.

Tensors changed: Embeddings 1/1, Norms 0/73, MLP 108/108, Attention 144/252

1 derivatives checked

• mradermacher/Qwen2.5-3B-Instruct-Perplexity-E3-BF16-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse