Supichi/BBAI_QWEEN_V000000_LUMEN_14B
Full fine-tune (fewer layers) vs Qwen/Qwen2.5-14B. Supichi/BBAI_QWEEN_V000000_LUMEN_14B matches part of Qwen/Qwen2.5-14B (387 of its 579 tensors; the rest of Qwen/Qwen2.5-14B has no counterpart). On the shared part: Fine-tune: 97% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, Norms 64/65, MLP 93/96, Attention 217/224, lm_head 1/1
1 derivatives checked
- mradermacher/BBAI_QWEEN_V000000_LUMEN_14B-GGUF: Same weights, converted