lightblue/suzume-llama-3-8B-multilingual-orpo-borda-half

Full fine-tune vs lightblue/suzume-llama-3-8B-multilingual. Fine-tune: 93% of the weights changed, across 32 of 32 layers.

Tensors changed: Embeddings 0/1, Norms 15/65, MLP 96/96, Attention 128/128, lm_head 1/1

1 derivatives checked

• featherless-ai-quants/lightblue-suzume-llama-3-8B-multilingual-orpo-borda-half-GGUF: Quantization

1 other repos hold byte-for-byte identical weight files.

On the Hub · Downloads on Model Pulse