arcee-ai/Virtuoso-Small-v2
Full fine-tune vs Qwen/Qwen2.5-14B. Fine-tune: 100% of the weights changed, across 48 of 48 layers.
Tensors changed: Norms 97/97, MLP 144/144, Attention 336/336
7 derivatives checked
- bartowski/arcee-ai_Virtuoso-Small-v2-GGUF: Same weights, converted
- mradermacher/Virtuoso-Small-v2-i1-GGUF: Quantization
- DevQuasar-7/arcee-ai.Virtuoso-Small-v2-GGUF: Same weights, converted
- sometimesanotion/Qwenvergence-14B-v13-Prose-DS: Full fine-tune
- tensopolis/virtuoso-small-v2-tensopolis-v1: LoRA-style
- jpacifico/Chocolatine-2-merged-qwen25arch: Full fine-tune
- CultriX/Qwen2.5-14B-Qwentangledv2: Partial fine-tune
1 other repos hold byte-for-byte identical weight files.