bunnycore/Llama-3.2-1b-Chatml-RP

Partial fine-tune vs bunnycore/Llama-3.2-1b-Mixer. Partial change: 82% of the weights changed (attention, embeddings, mlp), in 16 of 16 layers.

Tensors changed: lm_head 0/1, Embeddings 1/1, Norms 0/33, MLP 48/48, Attention 63/64

2 derivatives checked

• mradermacher/Llama-3.2-1b-Chatml-RP-i1-GGUF: Quantization
• mradermacher/Llama-3.2-1b-Chatml-RP-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse