inclusionAI/Ring-flash-2.0

Full fine-tune vs inclusionAI/Ling-flash-base-2.0. Fine-tune: 99% of the weights changed, across 32 of 32 layers.

Tensors changed: MLP 2683/2704, Attention 64/64, Norms 129/129, Embeddings 1/1, lm_head 1/1

3 derivatives checked

• mradermacher/Ring-flash-2.0-i1-GGUF: Quantization
• DevQuasar-11/inclusionAI.Ring-flash-2.0-GGUF: Quantization
• mradermacher/Ring-flash-2.0-GGUF: Quantization

On the Hub · Downloads on Model Pulse