Writer/palmyra-mini
Full fine-tune vs Qwen/Qwen2.5-1.5B. Fine-tune: 100% of the weights changed, across 28 of 28 layers.
Tensors changed: Norms 57/57, MLP 84/84, Attention 196/196
6 derivatives checked
- prithivMLmods/palmyra-mini-thinking-AIO-GGUF: Same weights, converted
- mradermacher/palmyra-mini-i1-GGUF: Quantization
- DevQuasar/Writer.palmyra-mini-GGUF: Same weights, converted
- mradermacher/palmyra-mini-GGUF: Same weights, converted
- Writer/palmyra-mini-GGUF: Same weights, converted
- Writer/palmyra-mini-MLX-BF16: Same weights, repacked