arcee-ai/Trinity-Nano-Preview
Full fine-tune vs arcee-ai/Trinity-Nano-Base. Fine-tune: 100% of the weights changed, across 56 of 56 layers.
Tensors changed: Embeddings 1/1, Norms 237/337, MLP 2378/2381, Attention 280/280, lm_head 1/1
14 derivatives checked
- arcee-ai/Trinity-Nano-Preview-GGUF: Same weights, converted
- dphn/Dolphin-X1-Trinity-Nano-GGUF: Quantization
- bartowski/arcee-ai_Trinity-Nano-Preview-GGUF: Same weights, converted
- mradermacher/Trinity-Nano-Preview-i1-GGUF: Quantization
- DevQuasar/arcee-ai.Trinity-Nano-Preview-GGUF: Same weights, converted
- mradermacher/Trinity-Nano-Preview-GGUF: Same weights, converted
- dphn/Dolphin-X1-Trinity-Nano: LoRA-style
- arcee-ai/Trinity-Nano-Preview-NVFP4: Quantization
- MaziyarPanahi/Trinity-Nano-Preview-GGUF: Same weights, converted
- professorf/Trinity-Nano-Preview-gguf: Same weights, converted
- arcee-ai/Trinity-Nano-Preview-MLX-6bit: Quantization
- arcee-ai/Trinity-Nano-Preview-W4A16: Quantization
- arcee-ai/Trinity-Nano-Preview-FP8-Block: Quantization
- Iambackup/Dolphin-X1-Trinity-Nano-GGUF: Quantization
2 other repos hold byte-for-byte identical weight files.