rombodawg/Rombos-Coder-V2.5-Qwen-14b
Full fine-tune vs Qwen/Qwen2.5-Coder-14B-Instruct. Fine-tune: 100% of the weights changed, across 48 of 48 layers.
Tensors changed: Embeddings 1/1, Norms 57/97, MLP 144/144, Attention 322/336, lm_head 1/1
4 derivatives checked
- bartowski/Rombos-Coder-V2.5-Qwen-14b-GGUF: Same weights, converted
- featherless-ai-quants/rombodawg-Rombos-Coder-V2.5-Qwen-14b-GGUF: Quantization
- mradermacher/Rombos-Coder-V2.5-Qwen-14b-GGUF: Quantization
- MaziyarPanahi/Rombos-Coder-V2.5-Qwen-14b-GGUF: Same weights, converted
1 other repos hold byte-for-byte identical weight files.