arcee-ai/Trinity-Large-Preview
Full fine-tune vs arcee-ai/Trinity-Large-Base. Fine-tune: 100% of the weights changed, across 60 of 60 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 361/361, MLP 2337/2337, Attention 300/300
7 derivatives checked
- unsloth/Trinity-Large-Preview-GGUF: Same weights, converted
- bartowski/arcee-ai_Trinity-Large-Preview-GGUF: Quantization
- DevQuasar/arcee-ai.Trinity-Large-Preview-GGUF: Quantization
- arcee-ai/Trinity-Large-Preview-FP8-Block: Quantization
- arcee-ai/Trinity-Large-Preview-W4A16: Quantization
- arcee-ai/Trinity-Large-Preview-FP8: Quantization
- arcee-ai/Trinity-Large-Preview-NVFP4: Quantization
4 other repos hold byte-for-byte identical weight files.