meditsolutions/Llama-3.2-SUN-1B-chat

Full fine-tune vs meta-llama/Llama-3.2-1B-Instruct. Fine-tune: 100% of the weights changed, across 16 of 16 layers.

Tensors changed: Embeddings 1/1, Norms 33/33, MLP 48/48, Attention 64/64

2 derivatives checked

• mradermacher/Llama-3.2-SUN-1B-chat-i1-GGUF: Full fine-tune
• mradermacher/Llama-3.2-SUN-1B-chat-GGUF: Full fine-tune

On the Hub · Downloads on Model Pulse