arcee-ai/Virtuoso-Small
Full fine-tune vs Qwen/Qwen2.5-14B. Fine-tune: 100% of the weights changed, across 48 of 48 layers.
Tensors changed: Embeddings 1/1, Norms 97/97, MLP 144/144, Attention 336/336, lm_head 1/1
9 derivatives checked
- sometimesanotion/Lamarck-14B-v0.7: Full fine-tune
- bartowski/Virtuoso-Small-GGUF: Quantization
- mradermacher/Virtuoso-Small-i1-GGUF: Quantization
- mradermacher/Virtuoso-Small-GGUF: Quantization
- DevQuasar-6/arcee-ai.Virtuoso-Small-GGUF: Quantization
- mergekit-community/VirtuosoSmall-InstructModelStock: Full fine-tune
- win10/miscii-Virtuoso-Small: Partial fine-tune
- neopolita/jessi-v0.1-virtuoso-small: Partial fine-tune
- neopolita/loki-v0.1-virtuoso: Partial fine-tune