inclusionAI/Ring-lite

Full fine-tune vs inclusionAI/Ling-lite-base-1.5. Fine-tune: 100% of the weights changed, across 28 of 28 layers.

Tensors changed: Embeddings 1/1, Norms 57/57, Attention 56/56, MLP 2885/2885, lm_head 1/1

2 derivatives checked

• mradermacher/Ring-lite-i1-GGUF: Full fine-tune
• mradermacher/Ring-lite-GGUF: Full fine-tune

On the Hub · Downloads on Model Pulse