u66u/Reyna-Mini-1.8B-v0.2-Qwen1.5-1.8B-Merged-Slerp

Full fine-tune vs Qwen/Qwen1.5-1.8B. Fine-tune: 97% of the weights changed, across 23 of 23 layers.

Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 47/47, MLP 66/69, Attention 154/161

1 derivatives checked

• mradermacher/Reyna-Mini-1.8B-v0.2-Qwen1.5-1.8B-Merged-Slerp-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse