trendmicro-ailab/Llama-Primus-Merged
Full fine-tune vs trendmicro-ailab/Llama-Primus-Base. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, Norms 65/65, MLP 96/96, Attention 128/128, lm_head 1/1
4 derivatives checked
- mradermacher/Llama-Primus-Merged-i1-GGUF: Quantization
- mradermacher/Llama-Primus-Merged-GGUF: Same weights, converted
- trendmicro-ailab/Llama-Primus-Reasoning: Full fine-tune
- DevQuasar-6/trendmicro-ailab.Llama-Primus-Merged-GGUF: Same weights, converted