arcee-ai/Trinity-Mini
Full fine-tune vs arcee-ai/Trinity-Mini-Base. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, Norms 124/193, MLP 2640/2645, Attention 160/160, lm_head 1/1
9 derivatives checked
- MaziyarPanahi/Trinity-Mini-GGUF: Same weights, converted
- bartowski/arcee-ai_Trinity-Mini-GGUF: Same weights, converted
- arcee-ai/Trinity-Mini-GGUF: Quantization
- mradermacher/Trinity-Mini-i1-GGUF: Quantization
- mradermacher/Trinity-Mini-GGUF: Quantization
- DevQuasar/arcee-ai.Trinity-Mini-GGUF: Same weights, converted
- arcee-ai/Trinity-Mini-NVFP4: Quantization
- arcee-ai/Trinity-Mini-FP8-Block: Quantization
- arcee-ai/Trinity-Mini-W4A16: Quantization
2 other repos hold byte-for-byte identical weight files.