Ereeeeef3/llama-3.3-merged

Partial fine-tune vs unsloth/Llama-3.3-70B-Instruct. Partial change: 48% of the weights changed (attention, mlp, norms), in 32 of 64 layers.

Tensors changed: Embeddings 0/1, Norms 64/129, MLP 96/192, Attention 128/256, lm_head 0/1

1 derivatives checked

• mradermacher/llama-3.3-merged-GGUF: Quantization

On the Hub · Downloads on Model Pulse