rombodawg/Rombos-Coder-V2.5-Qwen-7b
Full fine-tune vs Qwen/Qwen2.5-Coder-7B-Instruct. Fine-tune: 100% of the weights changed, across 28 of 28 layers.
Tensors changed: Embeddings 1/1, Norms 13/57, MLP 84/84, Attention 173/196, lm_head 1/1
6 derivatives checked
- bartowski/Rombos-Coder-V2.5-Qwen-7b-GGUF: Same weights, converted
- mradermacher/Rombos-Coder-V2.5-Qwen-7b-i1-GGUF: Quantization
- featherless-ai-quants/rombodawg-Rombos-Coder-V2.5-Qwen-7b-GGUF: Quantization
- mradermacher/Rombos-Coder-V2.5-Qwen-7b-GGUF: Same weights, converted
- benhaotang/Rombos-Coder-V2.5-Qwen-7b-GGUF_cline: Quantization
- MaziyarPanahi/Rombos-Coder-V2.5-Qwen-7b-GGUF: Same weights, converted
1 other repos hold byte-for-byte identical weight files.